@monte3l/groundwork 1.0.5 → 1.1.0

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 (32) hide show
  1. package/README.md +8 -1
  2. package/package.json +1 -1
  3. package/plugin/skills/customize/SKILL.md +17 -0
  4. package/plugin/skills/customize/step-3-round-1.md +82 -5
  5. package/plugin/src/pack-map.ts +57 -5
  6. package/plugin/src/plugin-map.ts +276 -27
  7. package/templates/core/.claude/settings.json +11 -1
  8. package/templates/core/.claude/skills/creating-prs/SKILL.md +1 -0
  9. package/templates/core/.claude/skills/finishing-work/SKILL.md +1 -0
  10. package/templates/core/.claude/skills/harness-guidance/SKILL.md +1 -0
  11. package/templates/core/.claude/skills/starting-work/SKILL.md +20 -0
  12. package/templates/core/.claude/skills/triaging-ci/SKILL.md +1 -0
  13. package/templates/core/.claude/skills/typescript-guidance/SKILL.md +1 -0
  14. package/templates/core/.claude/skills/writing-commits/SKILL.md +1 -0
  15. package/templates/core/CLAUDE.md +6 -3
  16. package/templates/packs/README.md +2 -0
  17. package/templates/packs/claude-github/files/.github/workflows/claude-pr-review.yml +1 -1
  18. package/templates/packs/claude-github/files/.github/workflows/claude.yml +1 -1
  19. package/templates/packs/frontend/files/.claude/agents/ui-reviewer.md +132 -0
  20. package/templates/packs/frontend/files/.claude/skills/new-component/SKILL.md +72 -0
  21. package/templates/packs/frontend/pack.json +19 -0
  22. package/templates/packs/github/files/.claude/skills/reviewing-dependabot-prs/SKILL.md +4 -0
  23. package/templates/packs/github/files/.claude/skills/triaging-scan-alerts/SKILL.md +3 -0
  24. package/templates/packs/github/files/.claude/skills/watching-pr-checks/SKILL.md +4 -0
  25. package/templates/packs/harness-extras/files/.claude/hooks/guard-readonly-bash.mjs +1117 -122
  26. package/templates/packs/harness-extras/pack.json +1 -1
  27. package/templates/packs/quality/files/.claude/agents/type-design-analyzer.md +1 -1
  28. package/templates/packs/service/files/.claude/agents/performance-analyzer.md +96 -0
  29. package/templates/packs/service/files/.claude/skills/api-doc/SKILL.md +67 -0
  30. package/templates/packs/service/files/.claude/skills/api-doc/openapi-template.yaml +48 -0
  31. package/templates/packs/service/pack.json +19 -0
  32. package/templates/packs/worktrees/files/.claude/skills/working-in-worktrees/SKILL.md +20 -5
@@ -6,6 +6,7 @@ description: >-
6
6
  path. Use for /creating-prs, "open a PR", "create a pull request", "ship
7
7
  this for review", "get this merged", or after finishing a fix. Requires gh
8
8
  CLI auth.
9
+ allowed-tools: Bash(git status --porcelain) Bash(git fetch origin) Bash(git log origin/main..HEAD --oneline) Bash(gh pr view *)
9
10
  ---
10
11
 
11
12
  # creating-prs
@@ -9,6 +9,7 @@ description: >-
9
9
  branch or stale refs linger -- even when it sounds like a one-line git
10
10
  command, because deleting a branch that never merged loses work and this
11
11
  skill checks first. GitHub stance: gh CLI.
12
+ allowed-tools: Bash(git status --porcelain) Bash(git worktree list --porcelain) Bash(gh pr view *)
12
13
  ---
13
14
 
14
15
  # finishing-work
@@ -11,6 +11,7 @@ description: >-
11
11
  up to date with Anthropic", "model pins current". Not how this project's
12
12
  harness is wired today — that's CLAUDE.md and the `.claude/` files
13
13
  themselves.
14
+ argument-hint: "[research <question> | refresh]"
14
15
  ---
15
16
 
16
17
  # harness-guidance
@@ -8,6 +8,7 @@ description: >-
8
8
  seen the code yet. Inspects git state, recommends a branch (feat/fix <slug>)
9
9
  and push target, and decides whether a PR is required, all confirmed before
10
10
  any write. Skip for research and questions that change nothing.
11
+ allowed-tools: Bash(git status --porcelain) Bash(git rev-parse --abbrev-ref HEAD) Bash(git rev-parse --git-path hooks) Bash(node --version)
11
12
  ---
12
13
 
13
14
  # starting-work
@@ -40,6 +41,25 @@ git status --porcelain # is the tree already dirty?
40
41
  - **Re-run this inspection after any conversational gap, not just at the
41
42
  start.** The branch is not a stable fact across a long session.
42
43
 
44
+ ### 1a — Environment preflight (read-only)
45
+
46
+ Before recommending anything, check that the checkout can actually run the
47
+ project's gates. This only reads and will report findings: **never install** anything and
48
+ never change a file, since a missing piece is the owner's call.
49
+
50
+ - **Node.** Compare `node --version` with the major in `.node-version` (the
51
+ project's authority for it). A mismatch is a finding, not an error.
52
+ - **Dependencies.** `node_modules` should exist. If it is missing, the
53
+ hooks and `pnpm verify` will fail until `pnpm install` is run.
54
+ - **Git hooks.** `lefthook`'s hooks should be installed in the checkout (look
55
+ for `pre-commit` and `pre-push` under the directory `git rev-parse --git-path hooks`
56
+ prints, which honours `core.hooksPath` and linked worktrees). If they are
57
+ missing, nothing runs the gates before a commit or push.
58
+
59
+ Report each finding in one line and carry on: they feed the Step 4 summary
60
+ and never block the branch decision. Skip a check whose file does not exist in
61
+ this project (no `.node-version`, no `lefthook.yml`).
62
+
43
63
  ### 2 — Infer the change scope
44
64
 
45
65
  From the task in front of you, work out **which paths will be edited** and
@@ -6,6 +6,7 @@ description: >-
6
6
  command, and present 3-5 fix options. Use for /triaging-ci, "why did CI fail",
7
7
  "CI is failing", "the build is red", "find the root cause of a failing
8
8
  build", "debug the CI run", or a specific run ID/URL. GitHub stance: gh CLI.
9
+ allowed-tools: Bash(gh run list *) Bash(gh run view *) Bash(git rev-parse --abbrev-ref HEAD)
9
10
  ---
10
11
 
11
12
  Diagnose why a GitHub Actions CI run failed by fetching its logs via `gh` and
@@ -15,6 +15,7 @@ description: >-
15
15
  we missing", or before changing a compiler flag. Not for a general Claude
16
16
  Code automation review, and not how this project's config is wired today
17
17
  — that's CLAUDE.md and the config files.
18
+ argument-hint: "[research <question> | refresh | gaps]"
18
19
  ---
19
20
 
20
21
  # typescript-guidance
@@ -5,6 +5,7 @@ description: >-
5
5
  imperative subject ≤70 chars, decide whether a body is needed, structure it as
6
6
  What → Why/How → semver impact, add Co-Authored-By when AI-assisted, then
7
7
  commit. Use for "commit this", "write a commit", "stage and commit".
8
+ allowed-tools: Bash(git status --porcelain)
8
9
  ---
9
10
 
10
11
  # writing-commits
@@ -126,9 +126,12 @@ on `Bash`, a missing `node` blocks every `Bash` call until fixed (run the
126
126
  command with the `!` prefix to get past it). The style guards and
127
127
  `guard-git-push-signed` stay fail-open on purpose: the push guard has its own
128
128
  parser and the remote's signed-commit rule is the authoritative layer.
129
- `permissions.deny` blocks `Read(./.env)`, `Read(./.env.*)` and
130
- `Read(./secrets/**)`, which also covers `cat`, `head` and `tail` on them in
131
- `Bash`. It does not cover `grep -r` or a script that opens the file itself.
129
+ `permissions.deny` blocks reading `.env`, `.env.*`, `secrets/`,
130
+ `credentials.json` and `secrets.yaml` (which also covers `cat`, `head` and
131
+ `tail` on them in `Bash`) and editing `pnpm-lock.yaml`, `package-lock.json`,
132
+ `yarn.lock` and the repository's `.git/` directory. It does not cover `grep -r`,
133
+ a script that opens the file itself, a subprocess such as `pnpm install`
134
+ rewriting the lock file, or a linked worktree, where `.git` is a file.
132
135
 
133
136
  **A spoke's `permissionMode` can be overridden.** A session in auto,
134
137
  `acceptEdits` or `bypassPermissions` mode overrides a spoke's `permissionMode`
@@ -108,6 +108,8 @@ already enumerate groups rather than individual steps.
108
108
  | `harness-extras` | Claude Code session hooks: the compaction-handoff hook pair (`PreCompact`, `SessionStart`) and a read-only Bash guard for review spokes. Registers hooks only; no top-level settings keys. |
109
109
  | `statusline` | A five-row `statusLine` (session, model, context, quota, work) plus a per-subagent row renderer. The only pack that sets top-level settings keys (`statusLine`, `subagentStatusLine`); a project that already defines either must decide on it, see its `adoptNotes`. |
110
110
  | `quality` | Two language-level review aids: a per-file size ratchet gate (`check-file-budget.mjs`, a `build`-group verify step) and a read-only `type-design-analyzer` agent. No hooks, no settings. Adopt-capable and recommended for every project kind. |
111
+ | `frontend` | Two aids for a project that builds UI: a read-only `ui-reviewer` agent (a static accessibility review of changed components, markup and styles against WCAG 2.2 at level AA, with anything needing a browser reported as `NOT CHECKED`) and a `new-component` skill that mirrors an existing sibling component's conventions and routes the work through `test-author`, `code-implementer` and `ui-reviewer`. No hooks, no settings, no gate, no framework templates. Adopt-capable; recommended only for the `frontend` kind. |
112
+ | `service` | Two aids for a project that serves an API: a read-only `performance-analyzer` agent (a static review of changed server code for blocking calls, per-request cost and unbounded work, with anything needing profiling or a load test reported as `NOT CHECKED`) and an `api-doc` skill that writes an OpenAPI description from the routes the code defines, using a template inside the skill. No hooks, no settings, no gate, no framework templates. Adopt-capable; recommended only for the `service` kind. |
111
113
  | `claude-github` | Anthropic's official Claude Code GitHub Action: one workflow wired for `@claude` mention-mode and a second that posts an automated Claude review comment on every PR. A pure file drop: no hooks, no gate. The workflows need an auth secret this pack cannot create and the review spends API credits per PR; see its `adoptNotes`. |
112
114
  | `github` | GitHub-hosted collaboration through the `gh` CLI: three skills — `reviewing-dependabot-prs`, `triaging-scan-alerts`, `watching-pr-checks`. No hooks, no gate, no workflows. `triaging-scan-alerts` needs code scanning turned on; see its `adoptNotes`. |
113
115
  | `publishing` | A release pipeline: `release.yml` (changesets version-PR / staged, provenance-attested npm publish via trusted publishing), `check-publish-version.mjs` and `check-dts-deps.mjs`. Fresh mode only; see "The wiring contract" above and its `adoptNotes`. |
@@ -86,7 +86,7 @@ jobs:
86
86
  fetch-depth: 0
87
87
 
88
88
  - id: claude
89
- uses: anthropics/claude-code-action@5eb090f3c3afd701a0672cd32981197ca27688f6 # v1.0.253
89
+ uses: anthropics/claude-code-action@db77d4d3c98f3f6380e7cd45ffba2342a3dbde3c # v1.0.254
90
90
  with:
91
91
  anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
92
92
  # Swap in CLAUDE_CODE_OAUTH_TOKEN or the Workload Identity
@@ -67,7 +67,7 @@ jobs:
67
67
  fetch-depth: 1
68
68
 
69
69
  - name: Run Claude Code
70
- uses: anthropics/claude-code-action@5eb090f3c3afd701a0672cd32981197ca27688f6 # v1.0.253
70
+ uses: anthropics/claude-code-action@db77d4d3c98f3f6380e7cd45ffba2342a3dbde3c # v1.0.254
71
71
  with:
72
72
  # Option 1 (active default): a stored API key. Install the Claude
73
73
  # GitHub App (https://github.com/apps/claude) and add
@@ -0,0 +1,132 @@
1
+ ---
2
+ name: ui-reviewer
3
+ description: Read-only UI accessibility reviewer. Does a static source review of changed components, markup and styles against WCAG 2.2 (level AA) and reports anything that needs a browser, a measurement or assistive technology as NOT CHECKED. Use after writing or changing UI. Complements code-reviewer (general structure and SOLID).
4
+ tools: Read, Grep, Glob
5
+ disallowedTools: Agent
6
+ model: claude-sonnet-5-5
7
+ effort: medium
8
+ maxTurns: 40
9
+ color: purple
10
+ ---
11
+
12
+ You are a UI accessibility reviewer for this project. You are read-only:
13
+ review and report; **never edit**. In the hub-and-spoke pipeline you are a
14
+ review spoke — you assess UI that a _different_ agent wrote
15
+ (normally `code-implementer`). That separation is the point: the author cannot grade
16
+ their own markup.
17
+
18
+ You have no shell. The hub names the files or directory to review in the
19
+ dispatch prompt; review exactly those. If you were given none,
20
+ return immediately with a request for a file list, since you cannot ask a
21
+ question mid-run. Do not widen the scope to the rest of the project.
22
+
23
+ ## What you can and cannot know
24
+
25
+ This is a **static review of source**. You can see missing text
26
+ alternatives, missing labels, a click handler on a non-interactive element, a
27
+ removed focus outline and an animation with no reduced-motion rule. You
28
+ cannot see rendered contrast, real focus order, layout at a narrow width or
29
+ how a screen reader announces a control. Report those as **NOT CHECKED** with
30
+ what would settle them, never as a pass. Never state that a page "conforms" or
31
+ "passes" WCAG: say what you found in the files you read, and what you did not
32
+ check.
33
+
34
+ The target is WCAG 2.2 (a W3C Recommendation of 12 December 2024) at level
35
+ AA. Level A criteria are part of AA. A criterion at level AAA is a
36
+ recommendation, never a Must-fix.
37
+
38
+ ## Checklist
39
+
40
+ Check each criterion only where the changed files give you something to look
41
+ at. Quote the criterion by number and title.
42
+
43
+ **Text alternatives and structure**
44
+
45
+ - **1.1.1 Non-text Content (A).** Every image, icon and non-text control has a
46
+ text alternative that serves the equivalent purpose; a purely decorative one
47
+ is hidden from assistive technology instead.
48
+ - **1.3.1 Info and Relationships (A).** Structure and relationships shown
49
+ visually are also in the markup: real headings, lists, tables and
50
+ form-control associations, not styled generic elements.
51
+ - **4.1.2 Name, Role, Value (A).** Every interactive component has a
52
+ programmatically determinable name and role, and its states can be set and
53
+ read. Prefer a native element (`button`, `a`, `input`) to a generic element
54
+ with a role added. The WAI-ARIA Authoring Practices Guide puts it plainly:
55
+ "No ARIA is better than Bad ARIA", because a role is a promise that the
56
+ element behaves like that role and ARIA adds no keyboard behaviour or styling
57
+ by itself.
58
+
59
+ **Keyboard and focus**
60
+
61
+ - **2.1.1 Keyboard (A).** All functionality works from a keyboard. A click
62
+ handler on a `div` or `span` that has no `tabindex` and no key handler cannot
63
+ be reached or operated from the keyboard, and fails this.
64
+ - **2.1.2 No Keyboard Trap (A).** Focus can move away from a component using
65
+ the keyboard alone. Look at dialogs and popovers: is there a keyboard-only
66
+ way out, such as Escape or a close button?
67
+ - **2.4.7 Focus Visible (AA).** A keyboard focus indicator is visible. Flag
68
+ `outline: none` or `outline: 0` (and an equivalent reset) with no replacement
69
+ style.
70
+ - **2.4.11 Focus Not Obscured (Minimum) (AA, new in WCAG 2.2).** A component
71
+ that receives keyboard focus is not entirely hidden by author-created
72
+ content such as a sticky header or a cookie banner. Usually **NOT CHECKED**
73
+ without a rendered page.
74
+
75
+ **Operable targets and forms**
76
+
77
+ - **2.5.8 Target Size (Minimum) (AA, new in WCAG 2.2).** A pointer target is at
78
+ least 24 by 24 CSS pixels, unless one of the criterion's exceptions applies
79
+ (enough spacing around an undersized target, an equivalent control on the
80
+ page, an inline target in a sentence, a size set by the user agent, or an
81
+ essential presentation). Flag explicit sizes below that on an interactive
82
+ element, and say which exception you checked.
83
+ - **3.3.2 Labels or Instructions (A).** A control that takes input has a label
84
+ or instructions. A `placeholder` that is the only label is a likely failure.
85
+ - **3.3.1 Error Identification (A).** An input error is identified and
86
+ described in text, not only by a colour or an icon.
87
+
88
+ **Colour, size and motion**
89
+
90
+ - **1.4.3 Contrast (Minimum) (AA).** Text has a contrast ratio of at least
91
+ 4.5:1, or 3:1 for large-scale text (at least 18 point, or 14 point bold).
92
+ Incidental text has no requirement: inactive user interface components, pure
93
+ decoration, text that is not visible, and logotypes.
94
+ - **1.4.11 Non-text Contrast (AA).** The parts of a control needed to identify
95
+ it and its states, and the parts of a graphic needed to understand it, have a
96
+ contrast ratio of at least 3:1 against adjacent colours.
97
+ For both contrast criteria, state a ratio only when the foreground and
98
+ background are literal values in the files you read and you can compute it;
99
+ a colour from a theme, a token you cannot resolve or an image is **NOT
100
+ CHECKED**. A background the files never set is not a literal value: do not
101
+ assume white or any default background, and do not quote a ratio against
102
+ it. Do not write a ratio figure at all in that case, even hedged as "about
103
+ 1.6:1" or "on white". Report it as **NOT CHECKED** and name the pair you would measure.
104
+ - **1.4.4 Resize Text (AA).** Text can be resized up to 200 percent without
105
+ loss of content or functionality.
106
+ - **1.4.10 Reflow (AA).** Content works at a width equivalent to 320 CSS pixels
107
+ without two-dimensional scrolling, except content that needs a
108
+ two-dimensional layout. Layout behaviour is **NOT CHECKED** unless a fixed
109
+ width in the source is clearly wider than that with no responsive rule.
110
+ - **2.3.3 Animation from Interactions (AAA).** Motion animation triggered by an
111
+ interaction can be disabled unless it is essential. Recommend a
112
+ `prefers-reduced-motion` rule for a new animation or transition, as a
113
+ Should-fix and never a Must-fix, because this criterion is level AAA.
114
+
115
+ ## Severity
116
+
117
+ - **Must-fix** — a failure of a level A or AA criterion that is evident from
118
+ the source you read.
119
+ - **Should-fix** — a likely failure that depends on something you could not
120
+ see, or a level AAA recommendation worth doing.
121
+ - **Nit** — minor, or a style point that improves robustness.
122
+ - **NOT CHECKED** — needs a rendered page, a measurement or assistive
123
+ technology. List these, with the check that would settle each one.
124
+
125
+ ## Report
126
+
127
+ Return a bounded digest inline, at most about 8,000 characters; never write a
128
+ file. For each finding give `file:line`, the criterion number and title, what
129
+ you saw, and the smallest fix. Group by Must-fix, Should-fix, Nit, then NOT
130
+ CHECKED. Stop once the checklist is answered for the files you were given: do
131
+ not re-verify indefinitely. If you found nothing in a category, say so in one
132
+ line.
@@ -0,0 +1,72 @@
1
+ ---
2
+ name: new-component
3
+ description: Adds a new component to a UI project by mirroring an existing sibling component's conventions, then runs it through the test-author, code-implementer and ui-reviewer loop. Use for /new-component, "add a new component", "scaffold a component", "create a UI component", or when asked for a component that should look and be tested like the ones already in the project.
4
+ argument-hint: "[component-name]"
5
+ ---
6
+
7
+ # new-component
8
+
9
+ A new component should look like the ones already in the project: same
10
+ folder layout, naming, props style, test style and, where the project has
11
+ them, story or example files. Shipping fixed templates would be wrong for
12
+ most projects (the framework is unknown here), so this skill reads a
13
+ **sibling** component and copies its conventions instead of inventing new
14
+ ones.
15
+
16
+ The hub plans and dispatches; it never writes `src/` or test code itself.
17
+ Writing is the job of `test-author` and `code-implementer`.
18
+
19
+ ## Steps
20
+
21
+ ### 1 — Find a sibling
22
+
23
+ Find the closest existing component to the one being asked for: same kind
24
+ (a form control, a layout piece, a list item), same folder, or the most
25
+ recently added. Read it in full, with its test file and any story or example
26
+ file beside it. Record, in a short list:
27
+
28
+ - the **framework** and file extensions in use (read them from the sibling
29
+ and from `package.json`; never assume one);
30
+ - where files live and how they are named (one folder per component or one
31
+ file, an index file, a barrel export);
32
+ - how props or inputs are typed, how state is held, how styles are attached;
33
+ - how the sibling is tested and what it asserts;
34
+ - how the sibling handles accessibility: element choice, labels, keyboard
35
+ handling, focus.
36
+
37
+ If there is no sibling (the project has no component yet), stop and ask the
38
+ owner which framework and conventions to use. Do not pick a framework and do
39
+ not add a **dependency** to make a component possible: a new package is a
40
+ decision for the owner, not a side effect of this skill.
41
+
42
+ ### 2 — Write the contract
43
+
44
+ Before any code, write the component's contract in a few lines: its name and
45
+ location (mirroring the sibling), its props or inputs, its states (default,
46
+ disabled, loading, error, empty), its keyboard behaviour, and its accessible
47
+ name and role. Settle the element first: prefer a native element (`button`,
48
+ `a`, `input`) over a generic element with a role added.
49
+
50
+ Confirm anything the sibling does not answer with the owner before going on.
51
+
52
+ ### 3 — Run the loop
53
+
54
+ 1. `test-author` writes failing tests from the contract, following the
55
+ sibling's test style, and confirms they fail for the right reason.
56
+ 2. `code-implementer` makes them pass, following the sibling's layout and
57
+ naming, and adds the story or example file only if the sibling has one.
58
+ 3. `ui-reviewer` reviews the new files for accessibility. Name the files to
59
+ review in the dispatch prompt, since it has no shell. `code-reviewer` runs
60
+ alongside it as usual.
61
+ 4. Must-fix findings go back to `code-implementer`, and the loop repeats until
62
+ clean.
63
+
64
+ If the project has no `test-author` or `code-implementer` (an adopted project
65
+ that dropped them), say so and stop: ask the owner to restore the writer
66
+ spokes, because the hub never writes `src/` itself.
67
+
68
+ ### 4 — Report
69
+
70
+ Say which sibling was mirrored, the files added, what `ui-reviewer` reported
71
+ including everything it listed as NOT CHECKED, and the checks only a browser
72
+ or a screen reader can settle.
@@ -0,0 +1,19 @@
1
+ {
2
+ "schemaVersion": 1,
3
+ "name": "frontend",
4
+ "description": "Two aids for a project that builds UI, on top of the baseline: a read-only ui-reviewer agent that does a static accessibility review of changed components, markup and styles against WCAG 2.2 (level AA, plus the animation criterion at AAA) and reports anything that needs a browser as NOT CHECKED, and a new-component skill that scaffolds a component by mirroring an existing sibling component's conventions and routing the work through the baseline's test-author, code-implementer and ui-reviewer loop. No hooks, no settings, no gate, no framework templates.",
5
+ "modes": ["fresh", "adopt"],
6
+ "budget": {
7
+ "agents": 1,
8
+ "skills": 1,
9
+ "hooks": 0,
10
+ "workflows": 0,
11
+ "scripts": 0
12
+ },
13
+ "wiring": {
14
+ "settings": {},
15
+ "packageScripts": {},
16
+ "verifySteps": []
17
+ },
18
+ "adoptNotes": "Both files install anywhere a .claude/ directory exists and need no gate runner. ui-reviewer is a read-only review spoke (model claude-sonnet-5-5 at medium effort, tools Read, Grep and Glob only, so it never runs a command): nothing in the baseline's hub-and-spoke instructions dispatches it by name, so ask for it after changing UI, or add it to the project's own CLAUDE.md review step. It reviews source statically and cannot measure contrast, focus order or layout, so it reports those as NOT CHECKED instead of guessing. new-component ships no framework templates: it reads an existing sibling component to learn the project's layout, naming and test conventions, so it works best with at least one component already in the project (with none it stops and asks the owner which conventions to use), and it hands the writing to test-author and code-implementer, which an adopted project must keep for the skill to work as written."
19
+ }
@@ -7,6 +7,8 @@ description: >-
7
7
  approve. Use for /reviewing-dependabot-prs, "review the dependabot PRs",
8
8
  "triage dependency updates", or when several Dependabot PRs have
9
9
  accumulated. GitHub stance: gh CLI.
10
+ allowed-tools: Bash(gh pr list *) Bash(gh pr view *) Bash(gh pr checks *)
11
+ disallowed-tools: Write, Edit, NotebookEdit
10
12
  ---
11
13
 
12
14
  Triage every open Dependabot pull request in this repository: classify each
@@ -16,6 +18,8 @@ skill never merges or closes a PR the user hasn't approved, and never
16
18
  guesses at a version bump's safety from the checks alone -- a major bump is
17
19
  always held for a human look, checks or no checks.
18
20
 
21
+ **Write and Edit are unavailable while this skill is active** (its `disallowed-tools`): it acts only through `gh`. A code fix for a failing update belongs in a fresh request or a spoke, not in this run.
22
+
19
23
  ## Steps
20
24
 
21
25
  ### 1 — List every open Dependabot PR
@@ -7,6 +7,7 @@ description: >-
7
7
  /triaging-scan-alerts, "review the scan alerts", "what does CodeQL flag",
8
8
  "triage the security findings", or after a code-scanning workflow run.
9
9
  GitHub stance: gh CLI.
10
+ disallowed-tools: Write, Edit, NotebookEdit
10
11
  ---
11
12
 
12
13
  Fetch every open code-scanning alert for this repository, group it by
@@ -15,6 +16,8 @@ file and line it points at. This skill produces a report and a set of
15
16
  options per alert -- it never edits code, dismisses an alert, or opens a
16
17
  PR on its own.
17
18
 
19
+ **Write and Edit are unavailable while this skill is active** (its `disallowed-tools`): it only reports. Fixing an alert belongs in a fresh request or a spoke, not in this run.
20
+
18
21
  ## Steps
19
22
 
20
23
  ### 1 — Fetch open alerts
@@ -7,6 +7,8 @@ description: >-
7
7
  check name alone. Use for /watching-pr-checks, "check this PR's status",
8
8
  "is this PR ready to merge", "did CI pass on my PR". GitHub stance: gh
9
9
  CLI.
10
+ allowed-tools: Bash(gh pr view *) Bash(gh pr checks *) Bash(gh run view *)
11
+ disallowed-tools: Write, Edit, NotebookEdit
10
12
  ---
11
13
 
12
14
  Check one pull request's CI status and act on what the checks actually
@@ -14,6 +16,8 @@ say, rather than assuming green or guessing at a failure. This is a
14
16
  single check, not a polling loop -- if checks are still running, report
15
17
  that plainly and let the user decide whether to ask again later or wait.
16
18
 
19
+ **Write and Edit are unavailable while this skill is active** (its `disallowed-tools`): it only reads check status. A fix for a red check belongs in a fresh request or a spoke after `/triaging-ci`, not in this run.
20
+
17
21
  ## Steps
18
22
 
19
23
  ### 1 — Resolve the PR