@igorlau/dotagents 1.0.20 → 1.0.22

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (108) hide show
  1. package/README.md +66 -66
  2. package/THIRD_PARTY_NOTICES.md +101 -6
  3. package/dist/build-info.json +1 -1
  4. package/dist/catalog.js +3 -3
  5. package/dist/cli.js +1 -1
  6. package/dist/commands.js +52 -15
  7. package/dist/manifest.js +8 -1
  8. package/dist/paths.js +0 -4
  9. package/dist/targets.js +3 -9
  10. package/dist/wizard.js +1 -1
  11. package/package.json +5 -3
  12. package/{plugin/rules → rules}/comments.upstream.json +1 -1
  13. package/{plugin/rules → rules}/ponytail.md +1 -1
  14. package/{plugin/rules → rules}/ponytail.upstream.json +1 -1
  15. package/{plugin/rules → rules}/writing.md +5 -2
  16. package/{plugin/rules → rules}/writing.upstream.json +1 -1
  17. package/{plugin/scaffold → scaffold}/AGENTS.md.tmpl +1 -1
  18. package/{plugin/skills → skills}/dot-code-review/SKILL.md +2 -0
  19. package/{plugin/skills → skills}/dot-code-review/UPSTREAM.json +1 -1
  20. package/skills/dot-code-review/references/finding-classes.md +33 -0
  21. package/{plugin/skills → skills}/dot-code-review/references/maintainability.md +1 -0
  22. package/{plugin/skills → skills}/dot-comments/UPSTREAM.json +1 -1
  23. package/{plugin/skills → skills}/dot-commit/SKILL.md +0 -2
  24. package/skills/dot-correct/UPSTREAM.json +8 -0
  25. package/{plugin/skills → skills}/dot-debug/UPSTREAM.json +1 -1
  26. package/{plugin/skills → skills}/dot-grilling/UPSTREAM.json +2 -2
  27. package/{plugin/skills → skills}/dot-handoff/UPSTREAM.json +1 -1
  28. package/{plugin/skills → skills}/dot-implement/SKILL.md +2 -2
  29. package/{plugin/skills → skills}/dot-implement/references/typescript.md +2 -1
  30. package/{plugin/skills → skills}/dot-plan/SKILL.md +3 -1
  31. package/{plugin/skills → skills}/dot-roadmap/SKILL.md +7 -4
  32. package/skills/dot-security-audit/SKILL.md +87 -0
  33. package/skills/dot-security-audit/UPSTREAM.json +8 -0
  34. package/skills/dot-security-audit/references/AI-AND-LLM.md +83 -0
  35. package/skills/dot-security-audit/references/ATTACK-CLASSES.md +130 -0
  36. package/skills/dot-security-audit/references/CLIENT-SIDE.md +83 -0
  37. package/skills/dot-security-audit/references/CLOUD-AND-DEPLOYMENT.md +86 -0
  38. package/skills/dot-security-audit/references/DATA-ISOLATION-AND-LIFECYCLE.md +84 -0
  39. package/skills/dot-security-audit/references/DESKTOP-MOBILE-AND-LOCAL-IPC.md +89 -0
  40. package/skills/dot-security-audit/references/MEMORY-SAFETY-AND-BINARY.md +101 -0
  41. package/skills/dot-security-audit/references/PROTOCOLS-RPC-AND-MESSAGING.md +81 -0
  42. package/skills/dot-security-audit/references/RESOURCE-EXHAUSTION-AND-AVAILABILITY.md +78 -0
  43. package/skills/dot-security-audit/references/SUPPLY-CHAIN-AND-RELEASE.md +73 -0
  44. package/skills/dot-security-audit/references/WEB-PROTOCOL-AND-AUTH.md +105 -0
  45. package/skills/dot-security-changes/SKILL.md +68 -0
  46. package/{plugin/skills → skills}/dot-testing/UPSTREAM.json +1 -1
  47. package/skills/dot-ui-review/SKILL.md +79 -0
  48. package/skills/dot-ui-review/UPSTREAM.json +8 -0
  49. package/skills/dot-ux-review/SKILL.md +50 -0
  50. package/skills/dot-ux-review/UPSTREAM.json +8 -0
  51. package/skills/dot-ux-review/references/web-interface-guidelines.md +191 -0
  52. package/{plugin/skills/dot-stack-review → skills/dot-walkthrough-branch}/SKILL.md +9 -30
  53. package/skills/dot-walkthrough-branch/references/layers.md +38 -0
  54. package/{plugin/skills/dot-stack-review → skills/dot-walkthrough-branch}/scripts/page.mjs +39 -10
  55. package/skills/dot-walkthrough-changes/SKILL.md +62 -0
  56. package/skills/dot-writing-for-agents/UPSTREAM.json +8 -0
  57. package/plugin/.claude-plugin/plugin.json +0 -10
  58. package/plugin/agents/dot-implementer.md +0 -27
  59. package/plugin/agents/dot-reviewer.md +0 -44
  60. package/plugin/agents/dot-tester.md +0 -25
  61. package/plugin/hooks/check.mjs +0 -118
  62. package/plugin/hooks/hooks.json +0 -54
  63. package/plugin/hooks/rules.mjs +0 -27
  64. package/plugin/skills/dot-correct/UPSTREAM.json +0 -8
  65. package/plugin/skills/dot-correct/agents/openai.yaml +0 -5
  66. package/plugin/skills/dot-debug/agents/openai.yaml +0 -3
  67. package/plugin/skills/dot-flow/SKILL.md +0 -105
  68. package/plugin/skills/dot-flow/agents/openai.yaml +0 -5
  69. package/plugin/skills/dot-flow/references/fix-round.md +0 -64
  70. package/plugin/skills/dot-flow/references/inline.md +0 -9
  71. package/plugin/skills/dot-grilling/agents/openai.yaml +0 -3
  72. package/plugin/skills/dot-handoff/agents/openai.yaml +0 -5
  73. package/plugin/skills/dot-roadmap/agents/openai.yaml +0 -5
  74. package/plugin/skills/dot-stack-review/agents/openai.yaml +0 -5
  75. package/plugin/skills/dot-writing-for-agents/UPSTREAM.json +0 -8
  76. package/plugin/skills/dot-writing-for-agents/agents/openai.yaml +0 -3
  77. /package/{plugin/rules → rules}/code-style.md +0 -0
  78. /package/{plugin/rules → rules}/comments.md +0 -0
  79. /package/{plugin/rules → rules}/core.md +0 -0
  80. /package/{plugin/scaffold → scaffold}/.claude/settings.json.tmpl +0 -0
  81. /package/{plugin/scaffold → scaffold}/.editorconfig.tmpl +0 -0
  82. /package/{plugin/scaffold → scaffold}/.gitattributes.tmpl +0 -0
  83. /package/{plugin/scaffold → scaffold}/CLAUDE.md.tmpl +0 -0
  84. /package/{plugin/skills → skills}/dot-comments/SKILL.md +0 -0
  85. /package/{plugin/skills → skills}/dot-correct/SKILL.md +0 -0
  86. /package/{plugin/skills → skills}/dot-debug/SKILL.md +0 -0
  87. /package/{plugin/skills → skills}/dot-debug/references/loops.md +0 -0
  88. /package/{plugin/skills → skills}/dot-debug/scripts/hitl-loop.template.sh +0 -0
  89. /package/{plugin/skills → skills}/dot-docs-writing/SKILL.md +0 -0
  90. /package/{plugin/skills → skills}/dot-docs-writing/references/formatting.md +0 -0
  91. /package/{plugin/skills → skills}/dot-docs-writing/references/global-and-accessible.md +0 -0
  92. /package/{plugin/skills → skills}/dot-docs-writing/references/word-list.md +0 -0
  93. /package/{plugin/skills → skills}/dot-grilling/SKILL.md +0 -0
  94. /package/{plugin/skills → skills}/dot-handoff/SKILL.md +0 -0
  95. /package/{plugin/skills → skills}/dot-implement/UPSTREAM.json +0 -0
  96. /package/{plugin/skills → skills}/dot-plan/UPSTREAM.json +0 -0
  97. /package/{plugin/skills → skills}/dot-plan/references/entity-schemas.md +0 -0
  98. /package/{plugin/skills → skills}/dot-roadmap/UPSTREAM.json +0 -0
  99. /package/{plugin/skills → skills}/dot-roadmap/references/wide-refactor.md +0 -0
  100. /package/{plugin/skills → skills}/dot-testing/SKILL.md +0 -0
  101. /package/{plugin/skills → skills}/dot-testing/references/after-implement.md +0 -0
  102. /package/{plugin/skills → skills}/dot-testing/references/http.md +0 -0
  103. /package/{plugin/skills → skills}/dot-testing/references/shared-state.md +0 -0
  104. /package/{plugin/skills → skills}/dot-testing/references/typescript.md +0 -0
  105. /package/{plugin/skills → skills}/dot-writing-for-agents/SKILL.md +0 -0
  106. /package/{plugin/skills → skills}/dot-writing-for-agents/references/pointers.md +0 -0
  107. /package/{plugin/skills → skills}/dot-writing-for-agents/references/skill-mechanics.md +0 -0
  108. /package/{plugin/skills → skills}/dot-writing-for-agents/references/steps.md +0 -0
@@ -0,0 +1,78 @@
1
+ # Resource Exhaustion and Availability Hunting
2
+
3
+ #### When to use this file
4
+
5
+ Reach for this file when untrusted requests, messages, files, tenant state, or agent work can consume CPU, memory, disk, connections, worker slots, paid APIs, or queue capacity, or can deadlock/crash a shared service. This domain distinguishes a source-reviewable availability vulnerability from a general performance issue. Never validate by stressing a shared or live service.
6
+
7
+ Use `MEMORY-SAFETY-AND-BINARY.md` for memory-integrity defects and `PROTOCOLS-RPC-AND-MESSAGING.md` for broker delivery logic. A reachable fatal error belongs here for shared impact even when the underlying parser is covered elsewhere.
8
+
9
+ ## Core discipline (include in every agent prompt for this domain)
10
+
11
+ ```
12
+ - Require an input-to-cost path, a missing effective bound, and impact on another user, shared service, safety function, or operator-owned spend. Self-limiting work in the requester's own process is not a service vulnerability.
13
+ - A missing rate limit is not enough. Check body/message/file caps, concurrency, queues, deadlines, database constraints, upstream gateways, and per-tenant quotas before calling a path unbounded.
14
+ - Do not run stress, saturation, or production tests. Use asymptotic analysis, small boundary fixtures, mocked paid calls, strict local resource limits, and deterministic cancellation tests.
15
+ - State attacker cost, service work, persistence, scope, and recovery. One bounded input with superlinear or persistent shared effect is materially different from sustained volume.
16
+ - Use `confirmed` for source-visible bounds failures demonstrated safely. Use `needs_validation` when upstream caps, deployed topology, autoscaling, paid quota, or recovery behavior is outside the repository.
17
+ ```
18
+
19
+ ## Computational amplification attack classes
20
+
21
+ **Superlinear parsing, matching, or evaluation**
22
+ Small accepted input drives catastrophic regex backtracking, nested parsing, recursive validation, symbolic evaluation, graph traversal, template expansion, or adversarial sort/hash behavior. Derive accepted depth/cardinality and complexity, then demonstrate a bounded growth curve locally.
23
+
24
+ **Decompression and representation amplification**
25
+ Compressed, sparse, nested, aliased, or encoded input expands far beyond the checked transfer or file size. Verify limits after every expansion and across parser stages, including archives, images, fonts, structured documents, and protocol compression tables.
26
+
27
+ **Database and downstream query amplification**
28
+ A small request creates broad scans, pathological joins, fan-out, unbounded sort/aggregation, or many downstream calls because query depth, filter cardinality, pagination, or expansion fields are not bounded. Confirm authorization does not intentionally permit the same resource scope.
29
+
30
+ ## Resource accumulation attack classes
31
+
32
+ **Unbounded buffering and cardinality**
33
+ Bodies, out-of-order streams, uploads, sessions, unique cache keys, metrics labels, log fields, subscriptions, or pending jobs accumulate without per-item and aggregate limits. Find cleanup and expiration on disconnect, timeout, cancellation, and partial parse.
34
+
35
+ **File descriptor, handle, and temporary-resource leaks**
36
+ Malformed or canceled work misses cleanup and retains sockets, files, database cursors, timers, subprocesses, temporary files, or object references. Confirm the leak repeats through bounded local iterations and affects a shared pool.
37
+
38
+ **Detached work after cancellation**
39
+ Client timeout, disconnect, canceled job, or failed authorization returns control but leaves database, model, network, or worker work running. Trace cancellation and deadline propagation through every layer.
40
+
41
+ ## Quota and scheduling attack classes
42
+
43
+ **Pre-authentication work imbalance**
44
+ Expensive parsing, key lookup, cryptography, decompression, or external requests happen before authentication and the earliest size/rate gate. Compare minimal requester effort to shared service cost and check upstream limits.
45
+
46
+ **Quota-accounting scope and reset gaps**
47
+ Accounting uses attacker-influenceable IP, route, tenant, key prefix, task ID, or other dimension, allowing one principal's work to escape its intended budget or consume another principal's allocation. Review integer overflow, distributed races, retries, reconnects, and account switching.
48
+
49
+ **Worker, pool, and priority starvation**
50
+ Low-priority or attacker-controlled jobs hold shared locks, workers, database pools, event-loop turns, or scheduler priority needed by unrelated users. Require a path that bypasses queue/concurrency fairness or retains a slot beyond its deadline.
51
+
52
+ ## Failure and recovery attack classes
53
+
54
+ **Reachable fatal error or deadlock**
55
+ An untrusted input reaches `panic`, abort, fatal assertion, unhandled exception, process exit, lock cycle, or infinite loop in a shared process. Confirm supervisor scope and whether one worker or the whole service becomes unavailable. A restarted isolated worker may reduce impact but does not erase the defect.
56
+
57
+ **Retry storm and fail-open amplification**
58
+ Timeouts, dependency errors, partially processed messages, or health-check failures trigger synchronized or unbounded retries without jitter, ceilings, circuit breaking, or deduplication. Verify one bounded failure source can create persistent aggregate work.
59
+
60
+ **Poison-record and head-of-line blocking**
61
+ One malformed record or message repeatedly fails at the front of a shared queue, partition, startup scan, migration, or recovery loop. Review skip/quarantine policy, offsets, and whether other tenants share the blocked unit.
62
+
63
+ **Unsafe recovery and capacity rollback**
64
+ A restart, restore, fallback, or cleanup path rebuilds unbounded state, ignores current quotas, or restores the input that immediately repeats failure. Recovery correctness is part of availability.
65
+
66
+ ## Universal moves (apply across the above)
67
+
68
+ - Build an input-to-resource table: earliest accepted size/cardinality, work before auth, downstream fan-out, persistence, shared pool, limit and cleanup owner, recovery.
69
+ - Compare aggregate limits with per-object limits. Ten thousand valid one-byte items may evade a per-message cap while exhausting tenant-wide or process-wide state.
70
+ - Validate only in an isolated fixture with strict CPU/memory/time limits and small growth points. Mock external and paid calls and stop once the missing bound or cancellation is observable.
71
+
72
+ ## Validation rules (apply before reporting ANY finding here)
73
+
74
+ 1. Name untrusted input, requester work, service amplification or retained resource, shared blast radius, and recovery. Missing limits without concrete shared impact are hardening.
75
+ 2. Confirm no source-visible upstream, parser, queue, tenant, or framework bound prevents the path. Unknown deployed controls require `needs_validation`.
76
+ 3. For superlinear behavior, establish the accepted complexity and bounded local growth. For leaks, show repeatable retention after cleanup should occur. For fatal paths, identify process/supervisor isolation.
77
+ 4. Prioritize by low requester work, unauthenticated reachability, cross-tenant scope, persistence, and poor recovery; do not validate with availability impact.
78
+ 5. Return `confirmed` only with safe local proof and meaningful shared effect. Return `needs_validation` with the exact upstream limit, topology, quota, or recovery observation an owner must check.
@@ -0,0 +1,73 @@
1
+ # Supply Chain and Release Hunting
2
+
3
+ #### When to use this file
4
+
5
+ Reach for this file when the target resolves dependencies, builds from untrusted contributions, runs CI, creates release artifacts, signs or promotes builds, loads plugins, or updates deployed software. This domain covers trust handoffs from source and dependency to the artifact a user runs. Use `MEMORY-SAFETY-AND-BINARY.md` for flaws inside a local binary loader and `CLOUD-AND-DEPLOYMENT.md` for runtime workload authority.
6
+
7
+ Split large targets into dependency resolution, CI isolation, artifact provenance, release authorization, and updater/plugin trust.
8
+
9
+ ## Core discipline (include in every agent prompt for this domain)
10
+
11
+ ```
12
+ - A mutable or known-vulnerable dependency is not a finding by itself. Show who can influence resolution, which build consumes it, and what execution or release boundary follows.
13
+ - Follow integrity across every handoff: source identity, resolved inputs, build worker, artifact identity, test result, signature/attestation, promotion, and update consumer.
14
+ - CI configuration is authorization code. Establish which event triggered a workflow, whose code runs, which secrets and tokens exist, and what it may publish or mutate.
15
+ - A checksum fetched from the same untrusted location as the artifact does not establish independent integrity. Identify the trusted root and failure behavior.
16
+ - Use `confirmed` for in-repo control-flow failures with bounded local validation. Use `needs_validation` for branch protection, hosted-runner, registry, signing-service, or production promotion facts that are not observable.
17
+ ```
18
+
19
+ ## Dependency and build-input attack classes
20
+
21
+ **Dependency source and namespace confusion**
22
+ Resolver configuration can select an unintended public/private namespace, fallback registry, mirror, repository, or source URL. Review package names, source priority, lockfile and checksum use, alternate build files, platform-specific resolution, and first-install versus update behavior.
23
+
24
+ **Mutable and unbound build inputs**
25
+ Builds consume branches, tags, unverified submodules, downloaded tools, generated assets, remote includes, floating CI actions, or container tags whose content can change without source review. Require a lower-trust writer and a path into trusted build output; reproducibility by itself does not prove authenticity.
26
+
27
+ **Generated-source and codegen provenance gaps**
28
+ Schemas, vendored archives, generated clients, localization, documentation examples, or binary blobs produce executable or shipped content without the same review and integrity gate as source. Compare local regeneration with committed output and verify who controls input and generator.
29
+
30
+ **Build-context inclusion**
31
+ Secrets, local configuration, repository metadata, test fixtures, or developer artifacts enter a package or image because the build context and ignore rules exceed intended release inputs. Confirm that the resulting artifact exposes a real credential, private data, or privileged configuration.
32
+
33
+ ## CI and automation attack classes
34
+
35
+ **Untrusted code in a privileged workflow**
36
+ A pull request, issue comment, fork, dependency update, or external event runs contributor-controlled code with protected secrets, write tokens, deployment authority, or a trusted runner. Compare trigger type, checkout ref, approval gate, environment protection, and permission narrowing. Do not assume repository-host defaults that are not in source.
37
+
38
+ **Workflow command and expression confusion**
39
+ Attacker-controlled branch names, commit messages, issue fields, artifact names, matrix values, or generated output enter shell commands, template expressions, paths, or privileged workflow inputs without canonical validation.
40
+
41
+ **Cache, artifact, and workspace trust mixing**
42
+ A lower-trust job can populate a cache, artifact, shared workspace, or output that a higher-trust job later restores and executes or releases. Review cache keys and namespaces, artifact producer identity, digest binding, retention, and whether promotion re-resolves by mutable name.
43
+
44
+ **Automation identity overreach**
45
+ CI jobs receive permissions beyond the operation, repository, environment, or duration needed, and untrusted job inputs can select the affected resource. Missing least privilege alone is hardening; require a reachable privileged action.
46
+
47
+ ## Release and update attack classes
48
+
49
+ **Build-to-promotion substitution**
50
+ Tests, review, signature, and publication refer to mutable tags, filenames, channels, or artifact IDs rather than the same immutable digest. Check every copy, repack, architecture merge, and provenance step between build and release.
51
+
52
+ **Release authorization and signing-policy gaps**
53
+ A release or signature is accepted from the wrong workflow, repository, branch, environment, key role, or threshold. Review identity claims inside attestations and verify the consumer validates them, not just a valid signature. Rotation, expiry, and revocation must fail closed where policy requires.
54
+
55
+ **Update metadata and rollback confusion**
56
+ An updater authenticates payload bytes but not version, product, platform, channel, target path, expiry, or rollback state, or it accepts metadata and payload from different authorized transactions. Verify atomic installation and recovery behavior. A signature API call without policy binding is incomplete.
57
+
58
+ **Plugin and extension trust expansion**
59
+ An extension package gains host authority beyond its declared scope, a lower-trust publisher can replace another publisher's identity, or install/update hooks run before authenticity and capability checks. Intended installation of arbitrary same-user plugins is not a privilege boundary.
60
+
61
+ ## Universal moves (apply across the above)
62
+
63
+ - Walk backward from a released digest or installed update to every source, generated input, credential, worker, cache, test result, and authorization decision.
64
+ - Compare untrusted and protected workflow events side by side. Mark each persisted channel crossing between them and require an immutable identity plus producer trust.
65
+ - Review revoked key, failed download, missing attestation, partial platform release, rollback, and registry outage paths. The failure policy is part of release integrity.
66
+
67
+ ## Validation rules (apply before reporting ANY finding here)
68
+
69
+ 1. Name the lower-trust actor, controllable source/cache/artifact/metadata, consuming trusted job or updater, and resulting unauthorized publication, code inclusion, secret disclosure, or privileged execution.
70
+ 2. Prove artifact identity across the broken handoff. A different mutable name or unbound digest must reach a real consumer.
71
+ 3. Verify built-in package-manager, repository-host, registry, and signing defaults for the pinned version. Unknown hosted controls require `needs_validation`.
72
+ 4. Keep local validation bounded: use a harmless fixture repository, dummy credential marker, local registry/config, and non-production artifact namespace. Do not publish or alter a real release.
73
+ 5. Return `confirmed` only with a complete source-visible handoff and meaningful result. Return `needs_validation` with the precise branch, runner, registry, signing, or deployment fact an owner must observe.
@@ -0,0 +1,105 @@
1
+ # HTTP-Protocol and Authentication Hunting
2
+
3
+ #### When to use this file
4
+
5
+ Reach for this file when the target speaks HTTP at a parsing, caching, browser-authentication, or identity boundary: web applications, APIs, reverse proxies, CDNs, gateways, custom HTTP servers, and services implementing sessions, JWT, OAuth/OIDC, SAML, password recovery, MFA, passkeys, API keys, or mTLS. Use this with `ATTACK-CLASSES.md`: access-control review asks whether a principal may perform an operation; this file asks whether the HTTP or identity layer can confuse which principal, request, assurance level, or token the operation belongs to.
6
+
7
+ Pick classes from the map step. Split a large target into request framing and cache policy, browser authentication, federated identity, strong authentication and recovery, service credentials, and session lifecycle. A single server behind an unobserved managed proxy has little source-confirmable smuggling surface; a proxy or custom parser has much more.
8
+
9
+ ## Core discipline (include in every agent prompt for this domain)
10
+
11
+ ```
12
+ - Framing and cache findings require two interpretations of the same request, response, or key. Name both components and the exact normalized value on each side.
13
+ - For every credential, find the signature or secret verification and every binding required for its role: issuer, audience, origin, RP, client, session, principal, resource, assurance, expiry, and one-time state.
14
+ - Host, Forwarded, X-Forwarded-*, Origin, Referer, redirect targets, callback state, and request-derived URLs are trust decisions. Trace each to the affected identity or response.
15
+ - A missing header, cookie attribute, MFA prompt, or rate limit is not a finding alone. Require an accepted invalid request, cross-principal impact, assurance downgrade, or credential disclosure.
16
+ - Classify `confirmed` only from complete source evidence and bounded local request/token tests. Use `needs_validation` when proxy, IdP, browser, certificate, secret, or deployed configuration is required but not visible.
17
+ ```
18
+
19
+ ## HTTP framing and cache attack classes
20
+
21
+ **Request framing and desynchronization**
22
+ Front end and back end disagree on request length or header normalization. Review multiple `Content-Length` values, `Transfer-Encoding`, HTTP/2 or HTTP/3 downgrade, header-name normalization, forbidden connection headers, and CR/LF conversion. Confirm which bytes one component assigns to a request and which bytes its peer assigns to the next request.
23
+
24
+ **Web cache poisoning through unkeyed input**
25
+ A request value changes cached content or security-relevant headers but is absent from the cache key. Compare cache key construction with every response variant, including forwarded host/scheme, selected cookies, query normalization, language/device headers, and authorization state.
26
+
27
+ **Cache deception and private-response caching**
28
+ Cache routing treats a private dynamic path as a public static asset, or caches a response whose identity and authorization inputs are missing from policy. Compare edge cacheability with application route parsing, suffix/path-parameter normalization, and response cache directives.
29
+
30
+ **Host and forwarded-header trust**
31
+ Untrusted host/proxy metadata determines absolute URLs, tenant routing, callbacks, reset links, cache keys, or the client address used by authorization. Confirm who can supply the header and whether trusted ingress removes client-provided copies.
32
+
33
+ **Response-header injection**
34
+ Untrusted data reaches `Location`, `Set-Cookie`, CSP, or another response header with unsafe control characters or normalization. Verify framework rejection before reporting and require a security-relevant response change.
35
+
36
+ ## Browser-session attack classes
37
+
38
+ **Ordinary CSRF**
39
+ A browser sends ambient credentials to a state-changing endpoint that accepts a cross-site request without an effective anti-CSRF token, same-site request binding, or strict Origin/Referer validation. Inventory every cookie-authenticated mutation, including form, JSON-like, multipart, method-override, and legacy routes. SameSite is effective only for the cookie and browser contexts actually used; login CSRF and cross-site subresource requests can have different requirements.
40
+
41
+ **Session fixation and invalidation**
42
+ Session identifiers are not rotated on login, account switch, MFA completion, impersonation, or other privilege changes, or remain valid after logout, password change, revocation, and account disable. Check server sessions, refresh tokens, signed cookies, websocket state, cache copies, and fallback endpoints.
43
+
44
+ **Cookie scope and transport**
45
+ A sensitive cookie has an over-broad `Domain` or `Path`, can cross an insecure transport, or conflicts with a sibling cookie that another component selects differently. Bare missing flags remain hardening notes unless a realistic less-trusted origin, network position, or browser path can gain or replace the credential.
46
+
47
+ ## Federated-identity attack classes
48
+
49
+ First establish role. Authorization-server controls such as redirect allowlisting and code issuance do not belong to a relying-party client. Verification and binding defects belong to the component consuming the artifact.
50
+
51
+ **JWT verification and claim binding**
52
+ Check signature verification, server-pinned algorithm and key source, then `exp`, `nbf`, `aud`, and `iss`. Review `kid`, `jku`, and `x5u` as untrusted key selectors, duplicate/header normalization, and decode-without-verify paths. A valid token for another service is invalid here even when signed by a trusted issuer.
53
+
54
+ **OAuth/OIDC request and callback binding**
55
+ Validate exact `redirect_uri` ownership where the target is the authorization server; session-bound `state`; PKCE and authorization-code binding where applicable; ID-token issuer/audience/signature/nonce; and selected-IdP binding in multi-provider flows. Compare initial callback, retry, mobile/deep-link, and account-link routes.
56
+
57
+ **SAML signed-object and assertion binding**
58
+ Ensure the element whose signature is validated is the element used as identity. Review unsigned/fallback paths, safe XML parser configuration, canonicalization differences, and freshness/binding fields such as validity windows, audience/recipient, request correlation, and replay state.
59
+
60
+ ## MFA, passkey, and account-transition attack classes
61
+
62
+ **MFA enrollment and assurance downgrade**
63
+ Enrollment, replacement, disablement, recovery-code generation, trusted-device creation, and fallback login require the intended prior assurance. Check that a valid first factor cannot enroll or replace the second factor without policy-required fresh authentication, and that disabled or stale factors stop authorizing sessions.
64
+
65
+ **Step-up binding and bypass**
66
+ A successful challenge upgrades the wrong session, account, tenant, action, or API request, or an alternate route omits the assurance check. Bind the challenge to principal, current session, assurance target, operation or resource when required, expiry, and one-time completion. Compare UI, API, batch, recovery, and resumed-flow paths.
67
+
68
+ **WebAuthn and passkey verification**
69
+ At registration, bind challenge, RP ID, expected origin, credential, user/userHandle, algorithm, and policy-required user verification to the initiating session. At authentication, verify challenge, RP/origin, credential membership, signature, and intended user presence/verification. Check account-discovery and linking flows for userHandle or credential-to-account confusion. Signature-counter handling is meaningful only when the product treats regressions as a clone signal.
70
+
71
+ **Account linking and identity collision**
72
+ Adding an IdP, passkey, email, phone, device, or external account to an existing account must require a current authenticated session, verified ownership of the new identity, policy-required step-up, and callback state bound to the account that initiated linking. Review unlink/relink and invite-acceptance paths for verified-identifier or tenant collisions.
73
+
74
+ **Password reset and broader recovery**
75
+ Recovery tokens, support/admin recovery, backup codes, device migration, and email or phone change often become the weakest authentication path. Verify token randomness, user/action binding, expiry, one-time state, rate/accounting controls, delivery URL trust, and invalidation of prior tokens and sessions. Different responses that only reveal public account existence are not automatically security findings.
76
+
77
+ ## API-key and mTLS attack classes
78
+
79
+ **API-key scope and resource binding**
80
+ A key authenticates to broader tenants, resources, actions, or environments than its server-side record grants, or request parameters override those bindings. Review key lookup, prefix/full-secret verification, type confusion between publishable and secret keys, scope checks, rotation, revocation caches, and bulk endpoints.
81
+
82
+ **API-key exposure and unsafe transport**
83
+ Keys appear in client bundles, URLs, redirects, logs, error paths, build artifacts, or responses accessible to a lower-trust principal. A public identifier called a key is not a secret. Confirm key type and the authority gained by disclosure.
84
+
85
+ **mTLS peer and application-identity confusion**
86
+ A process trusts client-certificate identity headers from any network peer, verifies a chain but maps attacker-influenceable subject text to an account incorrectly, or accepts a certificate for the wrong trust domain, extended usage, audience, or validity policy. Where a trusted proxy terminates mTLS, verify only that proxy can connect, it removes incoming identity headers, and the backend binds the sanitized identity to the request.
87
+
88
+ **Certificate lifecycle fallback**
89
+ Expired, revoked, missing, or renewal-failed certificates cause silent fallback to bearer-only or anonymous operation, or long-lived pooled connections retain authorization after revocation. Missing deployment revocation data makes the result `needs_validation`; an in-repo fail-open branch is source-confirmable.
90
+
91
+ ## Universal moves (apply across the above)
92
+
93
+ - Walk the steps issue, store, transmit, consume, refresh, and revoke for every credential and challenge. Compare normal, error, retry, migration, legacy, and account-switch paths.
94
+ - Enumerate every door to the same identity and every route to the same sensitive operation. The effective policy is the weakest parallel path, not the most polished UI.
95
+ - Diff parser, proxy, router, cache, and application normalization side by side. For local validation, feed identical bounded request fixtures into each component rather than sending traffic to a live deployment.
96
+ - For recovery and linking, draw the account before/after graph. Each edge must name the current principal, proof of the new identity, required assurance, callback/session binding, and revocation effect.
97
+
98
+ ## Validation rules (apply before reporting ANY finding here)
99
+
100
+ 1. Apply a source-visibility gate. Proxy chains, edge cache keys, IdP policy, certificate trust, browser cookie behavior, secrets, and deployed auth modes may be outside the repository. Record a precise `needs_validation` candidate instead of asserting missing infrastructure behavior.
101
+ 2. For framing and cache findings, name both components and the divergent parse/key. Confirm cross-request, cross-user, or private-response impact with bounded local fixtures.
102
+ 3. For token, MFA, passkey, account-link, recovery, API-key, and mTLS findings, cite the verification line and missing principal/session/resource/origin/audience/action/assurance binding. Prove the server accepts the invalid transition or credential.
103
+ 4. For CSRF, name the ambient credential, state-changing route, accepted cross-site request shape, browser cookie policy, and missing effective check. Read-only actions and routes requiring a non-ambient bearer token do not qualify.
104
+ 5. Verify framework and library defaults. If version or configuration is unknown, use `needs_validation`; do not turn an unverified critical claim into a lower-severity confirmed finding.
105
+ 6. Return `confirmed` only with a complete source trace and observable unauthorized identity, state, or disclosure. For `needs_validation`, name the missing fact and safe local or owner-observed check that resolves it.
@@ -0,0 +1,68 @@
1
+ ---
2
+ name: dot-security-changes
3
+ description: Check the uncommitted changes of the working tree, or the changes between two trees, for security problems. Use when the user or an agent asks for a security check of the current changes before a commit.
4
+ ---
5
+
6
+ # Security check of changes
7
+
8
+ Find vulnerabilities that the diff adds or exposes. This skill uses the rules of [`dot-security-audit`](../dot-security-audit/SKILL.md) for a boundary, a status, and a severity. It differs in the target, the references, and the report. For a whole codebase, use `dot-security-audit` instead.
9
+
10
+ ## 1. Pick the target
11
+
12
+ - **Working tree** (default): the working tree against `HEAD`. The diff is `git diff HEAD`, and each untracked file that `git status --porcelain` lists is a new file. Git ignores the files that `.gitignore` names, so they stay out.
13
+ - **Tree range**: `<old-tree> <new-tree>`, when the caller gives one. The diff is `git diff <old-tree> <new-tree>`.
14
+
15
+ Read each changed file from the working tree, or with `git show <tree>:<path>` for a tree range. For a deleted file, read it from `HEAD` or from the old tree.
16
+
17
+ State the target in one line: `working tree vs HEAD (<short sha>)`, or `<old-tree> .. <new-tree>`.
18
+
19
+ Done when you have the list of changed files. When there are none, stop and tell the user.
20
+
21
+ ## 2. Map the topics
22
+
23
+ For each changed hunk, name the topics that it touches. Read the reference of a topic only when a hunk touches that topic. Read no other reference.
24
+
25
+ | Topic of the diff | Read |
26
+ | ----------------- | ---- |
27
+ | SQL or shell strings, templates, file paths, redirects, URL fetches, deserialization, archives, input parsing, permission checks, secrets, tokens, randomness, or crypto | [`ATTACK-CLASSES.md`](../dot-security-audit/references/ATTACK-CLASSES.md) |
28
+ | HTTP handlers, middleware, sessions, cookies, CSRF, JWT, OAuth, SAML, MFA, passkeys, API keys, or mTLS | [`WEB-PROTOCOL-AND-AUTH.md`](../dot-security-audit/references/WEB-PROTOCOL-AND-AUTH.md) |
29
+ | Browser code, DOM rendering, a webview, a browser extension, a service worker, CORS, or WebSockets | [`CLIENT-SIDE.md`](../dot-security-audit/references/CLIENT-SIDE.md) |
30
+ | Prompts, retrieval, agent memory, tool calls, or an MCP server or client | [`AI-AND-LLM.md`](../dot-security-audit/references/AI-AND-LLM.md) |
31
+ | C, C++, or unsafe Rust, parsers of binary data, FFI, or loaders | [`MEMORY-SAFETY-AND-BINARY.md`](../dot-security-audit/references/MEMORY-SAFETY-AND-BINARY.md) |
32
+ | Dependency files, CI workflows, signing, release scripts, updates, or plugins | [`SUPPLY-CHAIN-AND-RELEASE.md`](../dot-security-audit/references/SUPPLY-CHAIN-AND-RELEASE.md) |
33
+ | IAM, infrastructure as code, containers, Kubernetes, serverless, or ingress | [`CLOUD-AND-DEPLOYMENT.md`](../dot-security-audit/references/CLOUD-AND-DEPLOYMENT.md) |
34
+ | gRPC, GraphQL, custom protocols, queues, brokers, or webhooks | [`PROTOCOLS-RPC-AND-MESSAGING.md`](../dot-security-audit/references/PROTOCOLS-RPC-AND-MESSAGING.md) |
35
+ | Loops, uploads, queries, or jobs that run untrusted work on shared CPU, memory, disk, workers, or spend | [`RESOURCE-EXHAUSTION-AND-AVAILABILITY.md`](../dot-security-audit/references/RESOURCE-EXHAUSTION-AND-AVAILABILITY.md) |
36
+ | Tenant scoping, caches, search, exports, backups, migrations, or deletion | [`DATA-ISOLATION-AND-LIFECYCLE.md`](../dot-security-audit/references/DATA-ISOLATION-AND-LIFECYCLE.md) |
37
+ | Native apps, deep links, webview bridges, local daemons, or sockets | [`DESKTOP-MOBILE-AND-LOCAL-IPC.md`](../dot-security-audit/references/DESKTOP-MOBILE-AND-LOCAL-IPC.md) |
38
+
39
+ When a hunk touches no topic, read no reference. Tell the user which references you read.
40
+
41
+ ## 3. Hunt
42
+
43
+ For each changed hunk, trace untrusted input to the dangerous sink, and check that each changed control checks the right permission on the right resource. Read the whole function and its callers: a hunk that looks safe can break a control elsewhere. Also check the code that the diff deletes. A removed check, validation, or escape is a candidate.
44
+
45
+ Write each candidate as a boundary hypothesis. Then apply the rules of "Rules for every finding" in [`dot-security-audit`](../dot-security-audit/SKILL.md#rules-for-every-finding), and drop each candidate that fails them. Do not report a problem in code that the diff does not change or expose. Run no target code unless the sandbox rules of `dot-security-audit` hold.
46
+
47
+ Done when you re-read the source of each candidate, searched for a control that stops it, and set its status.
48
+
49
+ ## 4. Report
50
+
51
+ Give the findings from most to least severe, in the format of [`dot-code-review`](../dot-code-review/SKILL.md#5-report), which accepts only `high`, `medium`, and `low`. Use the **Scenario** line for the boundary: the principal, the input, and the result. Use the severity anchors of `dot-security-audit`, and give only a `confirmed` finding a severity. Map `critical` to `high` and `informational` to `low`. Put a `needs_validation` finding after the `confirmed` findings, and give it its missing fact and a safe check in place of a severity. Add the smallest fix, and a regression test idea.
52
+
53
+ ```markdown
54
+ ### <high | medium | low> <one-line summary>
55
+ `path/to/file.ts:42` (security)
56
+ **Scenario:** <principal and input>, then <result>
57
+ **Fix:** <smallest change that enforces the invariant at the last trusted decision point>
58
+ ```
59
+
60
+ ```markdown
61
+ ### Needs validation: <one-line summary>
62
+ `path/to/file.ts:42` (security)
63
+ **Scenario:** <principal and input>, then <result>
64
+ **Missing fact:** <the one fact that blocks the proof>
65
+ **Check:** <safe way for the owner to check it>
66
+ ```
67
+
68
+ If you find nothing, say that the check found no security problems, and list the topics that you checked. Edit no file.
@@ -1,7 +1,7 @@
1
1
  {
2
2
  "repository": "https://github.com/cursor/plugins",
3
3
  "path": "pstack/skills/principle-test-behavior-not-implementation/SKILL.md",
4
- "commit": "a5539b15a3d56e04992565aafee2b37051329ce3",
4
+ "commit": "e58dd043600587dbaf58ba315e7f2b38373eeb43",
5
5
  "license": "MIT",
6
6
  "modified": true,
7
7
  "notes": "Condensed the principle into one clause of the assertion bullet in Test principles. The rest of the skill is original and is not from pstack."
@@ -0,0 +1,79 @@
1
+ ---
2
+ name: dot-ui-review
3
+ description: Review UI changes visually in a browser, against a live preview of the app, for interaction, responsive layout, visual polish, accessibility, and robustness. Use when the user or an agent asks for a UI or design review of front-end changes. Do not use it for a correctness review of the code: use `dot-code-review`. The review skips when the app cannot start or no browser tool exists.
4
+ ---
5
+
6
+ # UI review
7
+
8
+ Review the UI changes in a running app, in a browser, as a user sees them. Assess the live experience first, and read the code second. For a review that reads code only, use `dot-ux-review`.
9
+
10
+ Report findings as problems and their effect on the user. Assume that the author meant well. Change no code.
11
+
12
+ ## 1. Check the preconditions
13
+
14
+ The review needs both of these:
15
+
16
+ - **An app command.** Use the command that the caller gives. Otherwise use the `dev` script, then the `start` script, in `package.json` or in the build file of the project.
17
+ - **A browser tool.** Use the browser tool of the session: Playwright MCP or Claude in Chrome. Load its tools if they are deferred.
18
+
19
+ When one is missing, stop. Make no change and start nothing. Report this line with the reasons, and nothing else:
20
+
21
+ ```text
22
+ UI review: skipped. <reason>
23
+ ```
24
+
25
+ Use one of these reasons. Step 2 uses the last two:
26
+
27
+ - `no app command: the caller gave none, and the project has no dev or start script`
28
+ - `no browser tool: the session has neither Playwright MCP nor Claude in Chrome`
29
+ - `the app did not start: <the command and its last error line>`
30
+ - `no UI changes: the target has no file that renders a UI`
31
+
32
+ Done when you have the app command and a browser tool, or you reported the skip line.
33
+
34
+ ## 2. Prepare
35
+
36
+ 1. Pick the target: the working tree against `HEAD` (`git diff HEAD`, plus the untracked files that `git status --porcelain` lists), or the tree range `<old-tree> <new-tree>` that the caller gives. Read the description of the work, the pull request, or the roadmap task if there is one, for the motivation and the test notes.
37
+ 2. Read the diff. List the components, the routes, and the states that it changes. If the files render no UI, report the skip line with the reason `no UI changes`.
38
+ 3. Start the app command in the background. Do not install dependencies. Read its output for the local URL, and wait until the URL answers. If the app does not answer within 60 seconds, stop it, and report the skip line with the reason `the app did not start`.
39
+ 4. Open the URL in the browser. Set the desktop viewport to 1440 by 900.
40
+ 5. Run `git check-ignore -q .tmp/`. When Git ignores `.tmp`, save each screenshot in `.tmp/ui-review/`. Otherwise take no screenshot to disk, and report each visual finding without a path.
41
+
42
+ Use only the local app. Use dummy data in each form, and do not open a link to a deployed or shared service.
43
+
44
+ ## 3. Review in phases
45
+
46
+ Run the phases in order. In each phase, visit the pages and the states that the diff changes. Take a screenshot as evidence of each visual finding. Skip a phase check that the change does not touch.
47
+
48
+ 1. **Interaction and user flow.** Run the main flow of the change, following the test notes. Test the hover, active, focus, and disabled states. Check that a destructive action asks for confirmation. Judge how fast the interface answers.
49
+ 2. **Responsiveness.** Test the desktop viewport (1440 px), the tablet viewport (768 px), and the mobile viewport (375 px). Capture a screenshot of each. Check that the layout adapts, that touch targets are large enough, and that nothing scrolls sideways or overlaps.
50
+ 3. **Visual polish.** Check the alignment and the spacing, the typography hierarchy and the legibility, the colors and the image quality, and whether the visual hierarchy guides the eye.
51
+ 4. **Accessibility (WCAG 2.1 AA).** Tab through the whole change and check the order. Check a visible focus state on each interactive element, Enter and Space activation, semantic HTML, form labels, image alt text, and a contrast ratio of 4.5:1 or more for text.
52
+ 5. **Robustness.** Submit invalid input to each form. Test long text and large content for overflow. Check the loading, empty, and error states, and other edge cases.
53
+ 6. **Code health.** Read the changed code. Check that it reuses existing components, uses the design tokens of the project and not magic numbers, and follows the patterns of the project.
54
+ 7. **Content and console.** Check the grammar and the clarity of each text. Read the browser console for errors and warnings.
55
+
56
+ Done when each phase has run, or you wrote down why it did not apply.
57
+
58
+ ## 4. Clean up
59
+
60
+ Stop the app process that you started. Close the browser tabs that you opened.
61
+
62
+ ## 5. Report
63
+
64
+ Start with one or two sentences on what works well and on the overall quality. Then give the findings in the `dot-code-review` format, from most to least severe:
65
+
66
+ ```markdown
67
+ ### <high | medium | low> <one-line summary>
68
+ `path/to/Component.tsx:42` (ui)
69
+ **Cost:** <what the user pays, and the viewport or state where it shows>
70
+ **Screenshot:** `.tmp/ui-review/<name>.png`
71
+ **Fix:** <smallest change that removes the problem>
72
+ ```
73
+
74
+ - Use `file:line` of the component that renders the problem. When you cannot find the component, use the route.
75
+ - Use `high` for a failure that blocks the flow or an accessibility barrier, `medium` for a significant problem to fix before merge, and `low` for polish.
76
+ - Describe the problem and its effect. Name a fix only when it is small and clear.
77
+ - Omit the **Screenshot** line when the finding has no screenshot.
78
+
79
+ When you find nothing, say that the review found no UI problems, and list the viewports and the states that you checked.
@@ -0,0 +1,8 @@
1
+ {
2
+ "repository": "https://github.com/OneRedOak/claude-code-workflows",
3
+ "path": "design-review",
4
+ "commit": "29a34c725313c7621f426f838ed31cf482473fb4",
5
+ "license": "MIT",
6
+ "modified": true,
7
+ "notes": "Rewrote design-review-agent.md and design-review-slash-command.md as one SKILL.md under rules/writing.md, and renamed the skill with the dot- prefix. Kept the review phases 1 to 7 and the Live Environment First principle, and folded Phase 0 into a prepare step. Replaced the Playwright tool names with the browser tool of the session (Playwright MCP or Claude in Chrome). Added a precondition step that stops with the line \"UI review: skipped\" and a reason when the app command or the browser tool is missing. Replaced the triage matrix and the report structure with the dot-code-review finding format, with file:line and a screenshot path. Dropped the pull request diff injection, the tool list, the model and color settings, the context7 tools, design-principles-example.md, design-review-claude-md-snippet.md, and README.md."
8
+ }
@@ -0,0 +1,50 @@
1
+ ---
2
+ name: dot-ux-review
3
+ description: Review UI code for UX, accessibility, and interface rules by reading the code, against the Vercel web interface guidelines. Use when the user or an agent asks for a UX review of the current changes, or of a path, before a commit. Do not use it for a correctness review of the code: use `dot-code-review`.
4
+ ---
5
+
6
+ # UX review
7
+
8
+ Review UI code against the rules in [`web-interface-guidelines.md`](references/web-interface-guidelines.md). This skill reads code only. It starts no app and no browser. For a visual review in a browser, use `dot-ui-review`.
9
+
10
+ ## 1. Pick the target
11
+
12
+ - **Working tree** (default): the working tree against `HEAD`. The diff is `git diff HEAD`, and each untracked file that `git status --porcelain` lists is a new file. Git ignores the files that `.gitignore` names, so they stay out.
13
+ - **Tree range**: `<old-tree> <new-tree>`, when the caller gives one. The diff is `git diff <old-tree> <new-tree>`.
14
+ - **Path**: a file or a directory that the user names. Review the whole file.
15
+
16
+ Keep only the files that end in `.tsx`, `.jsx`, `.vue`, `.svelte`, `.html`, or `.css`. Read each one from the working tree, or with `git show <tree>:<path>` for a tree range. Skip a deleted file.
17
+
18
+ State the target in one line: `working tree vs HEAD (<short sha>)`, `<old-tree> .. <new-tree>`, or the path.
19
+
20
+ Done when you have the list of UI files. When there are none, stop and tell the user: `UX review: no UI files changed`.
21
+
22
+ ## 2. Read the rules
23
+
24
+ Read [`web-interface-guidelines.md`](references/web-interface-guidelines.md). Use its "Rules" and "Anti-patterns" sections. Ignore its frontmatter, its `$ARGUMENTS` line, and its "Output Format" section: step 4 sets the format.
25
+
26
+ ## 3. Check each file
27
+
28
+ For each UI file, read the whole file, not only the changed hunks. Check it against every section of the rules. A rule that does not apply to the file is not a finding, such as a form rule in a file with no form.
29
+
30
+ - With a diff target, report a finding only on a line that the diff adds or changes, or on a line whose result the change alters.
31
+ - Report a rule break that you can point to in the code. Do not guess at runtime behavior that the code does not show.
32
+ - When the repository has its own design system or component library, a component of it can meet a rule for you. Read the component before you report the rule as broken.
33
+ - Where the repository's own convention differs from a rule, follow the repository, and say so in one line at the end of the report. The rules use Title Case for headings and buttons, for example. A repository can use sentence case.
34
+
35
+ Done when you checked each UI file against each section of the rules.
36
+
37
+ ## 4. Report
38
+
39
+ Give the findings in the `dot-code-review` format, from most to least severe. Use `high` for an accessibility barrier or an anti-pattern from the rules, `medium` for another rule break that users meet, and `low` for polish:
40
+
41
+ ```markdown
42
+ ### <high | medium | low> <one-line summary>
43
+ `path/to/file.tsx:42` (ux)
44
+ **Cost:** <what the user or the next change pays>
45
+ **Fix:** <smallest change that removes the problem>
46
+ ```
47
+
48
+ Name the rule in the summary, such as "icon button has no `aria-label`". Group repeated breaks of one rule in one finding with the list of lines.
49
+
50
+ When you find nothing, say that the review found no UX problems, and list the files that you checked. Change code only when the user asks for fixes.
@@ -0,0 +1,8 @@
1
+ {
2
+ "repository": "https://github.com/vercel-labs/web-interface-guidelines",
3
+ "path": "command.md",
4
+ "commit": "434b7f91364665f2f733b310ec54809bf8f37937",
5
+ "license": "MIT",
6
+ "modified": true,
7
+ "notes": "Copied command.md as references/web-interface-guidelines.md. Replaced 7 em dashes and the contraction \"don't\" so that the file passes the writing lint. Changed no rule. The own SKILL.md ignores the frontmatter, the $ARGUMENTS line, and the Output Format section of the file."
8
+ }