ronce-racine 0.5.2 → 0.7.0

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 (64) hide show
  1. package/AGENTS.md +7 -2
  2. package/README.md +213 -207
  3. package/agents/code-reviewer.md +1 -1
  4. package/dist/hooks/README.md +62 -0
  5. package/dist/hooks/readme-freshness.mjs +159 -0
  6. package/dist/hooks/truncate-output.mjs +13 -5
  7. package/dist/install.js +114 -711
  8. package/dist/src/catalog.js +80 -0
  9. package/dist/src/detect.js +140 -0
  10. package/dist/src/lock.js +200 -0
  11. package/dist/src/paths.js +25 -0
  12. package/dist/src/selector.js +324 -0
  13. package/dist/src/settings.js +55 -0
  14. package/dist/src/uninstall.js +170 -0
  15. package/docs/adopting-a-repo.md +29 -22
  16. package/docs/architecture.md +9 -10
  17. package/docs/catalog.md +86 -0
  18. package/docs/decisions.md +31 -13
  19. package/docs/developing.md +69 -29
  20. package/docs/distribution-model.md +130 -0
  21. package/docs/evaluating-skills.md +42 -2
  22. package/docs/git-worktrees.md +2 -2
  23. package/docs/quality-bar.md +55 -0
  24. package/docs/templates/rule.template.md +2 -1
  25. package/docs/writing-a-rule.md +13 -3
  26. package/docs/writing-a-skill.md +16 -7
  27. package/package.json +17 -4
  28. package/skills/adversarial-feature-challenge/SKILL.md +5 -3
  29. package/skills/api-contract-versioning/SKILL.md +6 -4
  30. package/skills/bug-ticket-root-cause/SKILL.md +5 -3
  31. package/skills/bug-triage-structured/SKILL.md +5 -3
  32. package/skills/ci-pipeline-orchestration/SKILL.md +5 -3
  33. package/skills/commit-readiness-review/SKILL.md +7 -3
  34. package/skills/commit-readiness-review/scripts/precommit-scan.ts +3 -3
  35. package/skills/comprehensive-test-strategy/SKILL.md +5 -3
  36. package/skills/daily-workflow-optimization/SKILL.md +6 -4
  37. package/skills/database-schema-evolution/SKILL.md +6 -4
  38. package/skills/ddd-backend-implementation/SKILL.md +5 -3
  39. package/skills/design-system-component-lifecycle/SKILL.md +6 -4
  40. package/skills/detection-sweep/SKILL.md +7 -3
  41. package/skills/detection-sweep/scripts/sweep.ts +3 -3
  42. package/skills/domain-glossary/README.md +44 -0
  43. package/skills/domain-glossary/SKILL.md +166 -0
  44. package/skills/frontend-fullstack-implementation/SKILL.md +6 -4
  45. package/skills/frontend-spec-call-site-audit/SKILL.md +7 -3
  46. package/skills/frontend-spec-call-site-audit/scripts/audit-entry-points.ts +4 -1
  47. package/skills/merge-request-review/SKILL.md +5 -3
  48. package/skills/performance-profiling/README.md +69 -0
  49. package/skills/performance-profiling/SKILL.md +223 -0
  50. package/skills/performance-profiling/reference/go.md +235 -0
  51. package/skills/performance-profiling/reference/native.md +148 -0
  52. package/skills/performance-profiling/reference/node-web.md +157 -0
  53. package/skills/performance-profiling/reference/statistics.md +181 -0
  54. package/skills/performance-profiling/reference/tracy.md +137 -0
  55. package/skills/production-incident-diagnostic/SKILL.md +5 -3
  56. package/skills/qa-session-intake/SKILL.md +5 -3
  57. package/skills/recording-decisions/SKILL.md +5 -3
  58. package/skills/recurring-bug-root-cause/SKILL.md +5 -3
  59. package/skills/recurring-bug-root-cause/scripts/detect-recurring-fixes.ts +1 -1
  60. package/skills/refactoring-shared-component-api/SKILL.md +7 -3
  61. package/skills/refactoring-shared-component-api/scripts/sweep-call-sites.ts +10 -3
  62. package/skills/validating-features-end-to-end/SKILL.md +5 -3
  63. package/skills/visual-regression-check/SKILL.md +6 -4
  64. package/skills/writing-robust-tests/SKILL.md +8 -4
@@ -1,6 +1,7 @@
1
1
  ---
2
2
  # Limit injection to the relevant files (saves context).
3
- # Omit the whole frontmatter for an always-on rule.
3
+ # Drop the `paths` key (and only that key) for an always-on rule.
4
+ # `version` and `last-reviewed` are mandatory: `npm run rules:validate` fails without them.
4
5
  paths:
5
6
  - "**/*.ext"
6
7
  version: 1.0.0
@@ -30,14 +30,24 @@ metadata:
30
30
  - No magic numbers, no fluff.
31
31
  ```
32
32
 
33
- - **`paths:` frontmatter**: limits injection to the relevant files (saves context). Omitting it → always-active rule (reserve for cross-cutting rules like `commits.md`).
33
+ - **`paths:` frontmatter**: limits injection to the relevant files (saves context). Omitting **that key** → always-active rule (reserve for cross-cutting rules like `commits.md`); the frontmatter block itself stays, since the two fields below are mandatory.
34
34
  - **`version` (semver) + `metadata.last-reviewed`**: like skills (see [writing-a-skill.md](writing-a-skill.md)). Bump on every revision. Validated by `npm run rules:validate` (included in `npm test`).
35
35
  - No `<!-- ... -->` provenance comment: the source of truth is this repo, no need to repeat it (and Claude Code strips them from context anyway).
36
36
  - Keep it short: a long rule is followed less. Details and examples → a linked doc, not the rule.
37
37
 
38
38
  Ready-to-copy skeleton: [`templates/rule.template.md`](templates/rule.template.md).
39
39
 
40
+ ## The mandatory `docs/rules/<name>.md` page
41
+
42
+ A rule is a single file, so its human page lives under `docs/rules/` rather than next to it (see [developing.md](developing.md#what-travels-and-what-does-not)). `npm run rules:validate` **fails** without it, and checks two things beyond its existence:
43
+
44
+ - a `| **Version** | x.y.z |` cell holding the same version as the rule's frontmatter;
45
+ - a link back to the canonical artifact (`rules/<name>.md`).
46
+
47
+ The reverse also fails: a page under `docs/rules/` whose rule no longer exists. Copy an existing page for the shape - a one-line summary, a table of metadata, "What it enforces", "Why it matters", and where useful a short "How to apply it" with code.
48
+
40
49
  ## After adding / modifying
41
50
 
42
- 1. Update the rules table in the [README](../README.md).
43
- 2. Re-sync the repos that adopt the rule (`npx ronce-racine install <repo> --rules-only`), or let their CI gate report the drift.
51
+ 1. Add the rule to the `CATALOG` in [`src/catalog.ts`](../src/catalog.ts) with the signal that should propose it (`code`, `git`, `frontend`, `backend`, `sql`, `migrations`…). `tests/installer.test.ts` fails on a rule that exists on disk but no command can install.
52
+ 2. Update the rules table in the [README](../README.md).
53
+ 3. Re-sync the repos that adopt the rule (`npx ronce-racine install <repo> --rules-only`), or let their CI gate report the drift.
@@ -12,7 +12,10 @@ If the workflow is useful but coupled, **split it**: the generic *protocol* come
12
12
 
13
13
  ## What a complete skill looks like
14
14
 
15
- Every file below is required by a CI gate. A skill missing one of them fails `npm test`.
15
+ `SKILL.md` and `README.md` are required by `npm test` (`tools/skills.ts validate`),
16
+ and a `scripts/<x>.ts` without its `scripts/<x>.test.ts` fails the same command.
17
+ `eval.yaml` is validated by `npm run eval:dry`, a separate CI job: a skill that
18
+ ships without one is skipped rather than reported, so adding it is on you.
16
19
 
17
20
  ```
18
21
  skills/<name>/
@@ -103,16 +106,22 @@ A deterministic detection command belongs in `scripts/` ("Run `scripts/x.ts`") r
103
106
  ## Validation before opening a PR
104
107
 
105
108
  ```bash
106
- npm test # structure, bilingual trigger routing, versioning, behavioral tests
107
- npm run typecheck
109
+ npm run verify # typecheck + lint + structure, trigger routing, versioning, behavioral tests
108
110
  npm run test:mutation # every declared mutation must turn its tests red
109
111
  npm run eval:dry # every eval.yaml parses and names an existing fixture
110
112
  ```
111
113
 
112
- All four run in CI. The harness fails (exit 1) on any drift from the contract.
114
+ All of them run in CI. The harness fails (exit 1) on any drift from the
115
+ contract. What each gate covers - and what it structurally cannot see - is in
116
+ [developing.md](developing.md#what-each-gate-actually-protects).
113
117
 
114
118
  ## After adding / modifying
115
119
 
116
- 1. Bump `version` + `last-reviewed`, add a line to the `## Changelog`.
117
- 2. Update the skills table in the [README](../README.md).
118
- 3. The four commands above, green.
120
+ 1. Bump `version` + `last-reviewed`, add a line to the `## Changelog` (the
121
+ section itself is mandatory: `tools/skills.ts validate` requires it).
122
+ 2. Add the skill to the `CATALOG` in [`src/catalog.ts`](../src/catalog.ts) with
123
+ the signal that should propose it. `tests/installer.test.ts` fails on an
124
+ artifact that exists on disk but no command can install.
125
+ 3. Update the skills table in the [README](../README.md). Nothing gates that
126
+ table, so it is the line most likely to go stale.
127
+ 4. The commands above, green.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "ronce-racine",
3
- "version": "0.5.2",
3
+ "version": "0.7.0",
4
4
  "type": "module",
5
5
  "description": "Ronce Racine - generic Claude Code config (always-on rules + on-demand skills) with a distribution CLI",
6
6
  "license": "MIT",
@@ -17,6 +17,7 @@
17
17
  "scripts/",
18
18
  "templates/",
19
19
  "docs/",
20
+ "!docs/chardon/",
20
21
  "!docs/superpowers/",
21
22
  "AGENTS.md"
22
23
  ],
@@ -40,18 +41,30 @@
40
41
  "scripts": {
41
42
  "build": "tsx tools/build.ts",
42
43
  "typecheck": "tsc --noEmit",
43
- "test": "tsx tools/skills.ts validate && tsx tools/skills.ts triggers && tsx tools/skills.ts rules && tsx tools/skills.ts scripts && tsx tools/skills.ts hooks && tsx tools/skills.ts templates && tsx tools/skills.ts docs && tsx tools/tests.ts",
44
+ "lint": "biome check .",
45
+ "lint:fix": "biome check --write .",
46
+ "verify": "npm run typecheck && npm run lint && npm test",
47
+ "test": "tsx tools/skills.ts validate && tsx tools/skills.ts triggers && tsx tools/skills.ts routing && tsx tools/skills.ts rules && tsx tools/skills.ts scripts && tsx tools/skills.ts hooks && tsx tools/skills.ts agents && tsx tools/skills.ts templates && tsx tools/skills.ts docs && vitest run",
44
48
  "test:mutation": "tsx tools/mutations.ts",
45
49
  "eval:dry": "tsx playground/setup.ts >/dev/null && tsx tools/eval.ts run --dry-run",
46
50
  "skills:list": "tsx tools/skills.ts list",
47
51
  "skills:triggers": "tsx tools/skills.ts triggers",
48
52
  "rules:validate": "tsx tools/skills.ts rules",
49
53
  "prepare": "tsx tools/build.ts",
50
- "prepublishOnly": "tsx tools/build.ts && npm test"
54
+ "prepublishOnly": "tsx tools/build.ts && npm test",
55
+ "test:watch": "vitest",
56
+ "coverage": "vitest run --coverage",
57
+ "test:mutation:inprocess": "stryker run"
51
58
  },
52
59
  "devDependencies": {
60
+ "@biomejs/biome": "^2.5.7",
61
+ "@stryker-mutator/core": "^9.6.1",
62
+ "@stryker-mutator/vitest-runner": "^9.6.1",
53
63
  "@types/node": "^22.0.0",
64
+ "@vitest/coverage-v8": "^4.1.10",
65
+ "fast-check": "^4.9.0",
54
66
  "tsx": "^4.0.0",
55
- "typescript": "^5.0.0"
67
+ "typescript": "^5.0.0",
68
+ "vitest": "^4.1.10"
56
69
  }
57
70
  }
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: adversarial-feature-challenge
3
3
  description: Use when a feature is "done" and needs adversarial stress-testing before shipping - "is it really ready", "est-ce vraiment prêt", "find the bugs", "trouve les bugs", "red team", before closing a ticket whose only validation is the golden path passing.
4
- version: 1.1.0
4
+ version: 1.1.1
5
5
  metadata:
6
- last-reviewed: 2026-07-21
6
+ last-reviewed: 2026-08-08
7
7
  category: feature
8
8
  ---
9
9
 
10
10
  # Adversarial feature challenge
11
11
 
12
- > If the current repo has a specific challenge skill (e.g. acme-app → `feature-challenge`), it wins.
12
+ > If the current repo has a specific challenge skill, it wins.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -91,6 +91,8 @@ metadata:
91
91
 
92
92
  ## Changelog
93
93
 
94
+ - 1.1.1 (2026-08-08) - dropped the fictional example projects from the precedence note
95
+
94
96
  - 1.1.0 (2026-07-21) - persona switch made explicit and countable; eval runs showed agents stopping after one
95
97
 
96
98
  - 1.0.0 (2026-06-19) - initial versioned release + state-of-the-art enrichment (routing, context, protocol, traps, exit condition)
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: api-contract-versioning
3
3
  description: Use when modifying an API endpoint, schema or contract consumed elsewhere - renaming/removing/restructuring a request or response field, pagination or envelope change, "field X must become", "le champ X doit devenir", introducing a breaking change, versioning an API, or deprecating a field/route. Covers REST, GraphQL and gRPC alike.
4
- version: 1.0.0
4
+ version: 1.0.1
5
5
  metadata:
6
- last-reviewed: 2026-06-19
6
+ last-reviewed: 2026-08-08
7
7
  category: feature
8
8
  ---
9
9
 
10
10
  # Versioning a network API contract
11
11
 
12
- > If the current repo has a specific skill or conventions for this case (e.g. acme-app → `api-contract-evolution`), they win - they know the project's paths, snapshots and stack.
12
+ > If the current repo has a specific skill or conventions for this case, they win - they know the project's paths, snapshots and stack.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -73,4 +73,6 @@ A network API contract has a chain of consumers that are **coupled and potential
73
73
 
74
74
  ## Changelog
75
75
 
76
- - 1.0.0 (2026-06-19) - initial release, generalized from the acme-app `api-contract-evolution` workflow (decoupled from a Rust/Axum stack, agnostic across REST/GraphQL/gRPC)
76
+ - 1.0.1 (2026-08-08) - dropped the fictional example projects from the precedence note
77
+
78
+ - 1.0.0 (2026-06-19) - initial release, generalized from a project-specific `api-contract-evolution` workflow (decoupled from a Rust/Axum stack, agnostic across REST/GraphQL/gRPC)
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: bug-ticket-root-cause
3
3
  description: Use when reporting or documenting an observed bug as a ticket (any tracker - GitLab, Jira, GitHub) - "report a bug", "signale un bug", "create a bug ticket", "crée un ticket de bug", "it doesn't work", "ça ne marche pas", a regression to document without fixing it now.
4
- version: 1.0.0
4
+ version: 1.0.1
5
5
  metadata:
6
- last-reviewed: 2026-06-19
6
+ last-reviewed: 2026-08-08
7
7
  category: bug
8
8
  ---
9
9
 
10
10
  # Bug ticket with root cause
11
11
 
12
- > If the current repo has a specific ticketing skill (e.g. acme-app → `add-bug`, beta-app → `jira-bug`), it wins - this skill defines the **content**, the project skill defines the **format/tracker**.
12
+ > If the current repo has a specific ticketing skill, it wins - this skill defines the **content**, the project skill defines the **format/tracker**.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -83,4 +83,6 @@ If the scope has already had 2+ recent fixes → a "Recurrence" section in the t
83
83
 
84
84
  ## Changelog
85
85
 
86
+ - 1.0.1 (2026-08-08) - dropped the fictional example projects from the precedence note
87
+
86
88
  - 1.0.0 (2026-06-19) - initial versioned release + state-of-the-art enrichment (routing, context, protocol, traps, exit condition)
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: bug-triage-structured
3
3
  description: Use when a bug needs full triage before deciding what to do with it - "reproduce and analyze this bug", "reproduis et analyse ce bug", "fix now or open a ticket?", "faut-il corriger maintenant ou ouvrir un ticket", "triage this bug", "trie ce bug", a fresh bug report where reproduction and root cause are still unknown. NOT for merely documenting an already-understood bug.
4
- version: 1.1.0
4
+ version: 1.1.1
5
5
  metadata:
6
- last-reviewed: 2026-07-21
6
+ last-reviewed: 2026-08-08
7
7
  category: bug
8
8
  ---
9
9
 
10
10
  # Structured bug triage - reproduce, understand, decide
11
11
 
12
- > If the current repo has a specific triage/ticketing skill (e.g. acme-app → `add-bug`, beta-app → `jira-bug`), it wins - it knows the project's tracker, paths and commands.
12
+ > If the current repo has a specific triage/ticketing skill, it wins - it knows the project's tracker, paths and commands.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -99,6 +99,8 @@ If the scope has already had 2+ recent fixes → apply `recurring-bug-root-cause
99
99
 
100
100
  ## Changelog
101
101
 
102
+ - 1.1.1 (2026-08-08) - dropped the fictional example projects from the precedence note
103
+
102
104
  - 1.1.0 (2026-07-21) - recurrence check made mechanical (git log command, count stated even when zero); eval runs showed agents skipping it
103
105
 
104
106
  - 1.0.0 (2026-06-19) - initial release: project-agnostic generalization of the add-bug workflow into full triage (repro → root-cause → decision → confirmation)
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: ci-pipeline-orchestration
3
3
  description: Use when a CI pipeline needs checking after a push, when CI is red and the failure must be diagnosed, when jobs need retrying, or when validating post-deploy HTTP headers and smoke tests. Triggers on "check the pipeline", "vérifier le pipeline", "rerun CI", "relancer CI", "the pipeline failed", "le pipeline a échoué", "validate the headers", "valider les headers", after any `git push`.
4
- version: 1.0.0
4
+ version: 1.0.1
5
5
  metadata:
6
- last-reviewed: 2026-06-19
6
+ last-reviewed: 2026-08-08
7
7
  category: process
8
8
  ---
9
9
 
10
10
  # CI Pipeline Orchestration - drive the pipeline end-to-end after a push
11
11
 
12
- > If the current repo has a project-specific pipeline skill (e.g. acme-app → `pipeline-orchestration`), it wins - it knows the CI provider, its commands and the deploy URLs.
12
+ > If the current repo has a project-specific pipeline skill, it wins - it knows the CI provider, its commands and the deploy URLs.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -107,4 +107,6 @@ Pipeline still `failed` with no ticket and no fix = not done.
107
107
 
108
108
  ## Changelog
109
109
 
110
+ - 1.0.1 (2026-08-08) - dropped the fictional example projects from the precedence note
111
+
110
112
  - 1.0.0 (2026-06-19) - initial version, derived from a project workflow and decoupled from the CI provider
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: commit-readiness-review
3
3
  description: Use before any Claude-initiated git commit - "ready to commit", "commit that", "quick commit", "prêt à commit", "commit ça", "vite un commit", time pressure to ship, diff containing test/debug leftovers or touching multiple stacks.
4
- version: 1.0.1
4
+ version: 1.0.3
5
5
  metadata:
6
- last-reviewed: 2026-07-20
6
+ last-reviewed: 2026-08-08
7
7
  category: process
8
8
  ---
9
9
 
10
10
  # Commit Readiness Review - self-review before committing
11
11
 
12
- > If the current repo has a project-specific pre-commit skill (e.g. acme-app → `pre-commit-self-review`), it wins - it knows the exact commands.
12
+ > If the current repo has a project-specific pre-commit skill, it wins - it knows the exact commands.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -77,6 +77,10 @@ A missing box = no commit.
77
77
 
78
78
  ## Changelog
79
79
 
80
+ - 1.0.3 (2026-08-08) - dropped the fictional example projects from the precedence note
81
+
82
+ - 1.0.2 (2026-08-08) - precommit-scan.ts iterates instead of returning a value from forEach
83
+
80
84
  - 1.0.1 (2026-07-20) - co-located test procedure for precommit-scan.ts (scripts/precommit-scan.test.ts)
81
85
 
82
86
  - 1.0.0 (2026-06-19) - initial versioned release + state-of-the-art enrichment (routing, context, protocol, traps, exit condition)
@@ -49,7 +49,7 @@ if (installed("gitleaks")) {
49
49
  const hits = addedLines.filter((l) => secretRe.test(l));
50
50
  if (hits.length) {
51
51
  console.log("✗ Potential SECRET (grep fallback - install gitleaks for reliability):");
52
- hits.forEach((l) => console.log(" " + l));
52
+ for (const l of hits) console.log(` ${l}`);
53
53
  secretHits = 1;
54
54
  }
55
55
  }
@@ -61,7 +61,7 @@ const sensitive = sh("git diff --cached --name-only")
61
61
  let sensitiveHits = 0;
62
62
  if (sensitive.length) {
63
63
  console.log("✗ SENSITIVE FILE staged:");
64
- sensitive.forEach((f) => console.log(" " + f));
64
+ for (const f of sensitive) console.log(` ${f}`);
65
65
  sensitiveHits = 1;
66
66
  }
67
67
 
@@ -71,7 +71,7 @@ const debugRe =
71
71
  const dbg = addedLines.filter((l) => debugRe.test(l));
72
72
  if (dbg.length) {
73
73
  console.log("⚠ DEBUG - potential leftovers (check, remove if unwanted):");
74
- dbg.forEach((l) => console.log(" " + l));
74
+ for (const l of dbg) console.log(` ${l}`);
75
75
  }
76
76
 
77
77
  if (secretHits + sensitiveHits > 0) {
@@ -1,9 +1,9 @@
1
1
  ---
2
2
  name: comprehensive-test-strategy
3
- description: Use when defining or auditing the test strategy of a module or whole project - building a coverage matrix by risk, choosing the test pyramid split, prioritizing what to test first, deciding which surfaces deserve which test level - "define the test strategy", "définis la stratégie de test", "coverage matrix by risk", "matrice de couverture". Not for writing the tests of one targeted file.
4
- version: 1.0.0
3
+ description: Use when defining or auditing the test strategy of a module or whole project - building a coverage matrix by risk, choosing the test pyramid split, prioritizing what to test first, deciding which surfaces deserve which test level - "define the test strategy", "définis la stratégie de test", "coverage matrix by risk", "matrice de couverture". Not for writing the tests of one targeted file - that is `writing-robust-tests`.
4
+ version: 1.0.1
5
5
  metadata:
6
- last-reviewed: 2026-06-19
6
+ last-reviewed: 2026-08-08
7
7
  category: test
8
8
  ---
9
9
 
@@ -105,4 +105,6 @@ Tickets: <list of follow-up tickets created>
105
105
 
106
106
  ## Changelog
107
107
 
108
+ - 1.0.1 (2026-08-08) - the exclusion clause now names the skill it redirects to
109
+
108
110
  - 1.0.0 (2026-06-19) - initial release, generalized from a project workflow (coverage matrix, risk prioritization, pyramid), stack/tracker coupling removed.
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: daily-workflow-optimization
3
3
  description: Use when reviewing recurring development workflow friction - "what's slowing things down", "qu'est-ce qui nous ralentit", periodic toil review, cutting repeated manual steps, identical recurring feedback/fixes, stale memories or context to refresh.
4
- version: 1.0.0
4
+ version: 1.0.1
5
5
  metadata:
6
- last-reviewed: 2026-06-19
6
+ last-reviewed: 2026-08-08
7
7
  category: process
8
8
  ---
9
9
 
10
10
  # Daily Workflow Optimization - cut workflow friction, not fix code
11
11
 
12
- > If the current repo has a tooled improvement command (e.g. acme-app → `daily-improve`), it wins - it knows its metrics, scripts and paths.
12
+ > If the current repo has a tooled improvement command, it wins - it knows its metrics, scripts and paths.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -77,4 +77,6 @@ If the repo exposes a measurement tool (metrics script, report), use it - it win
77
77
 
78
78
  ## Changelog
79
79
 
80
- - 1.0.0 (2026-06-19) - initial version, generalized from acme-app's daily-improve workflow (metrics/scripts coupling removed)
80
+ - 1.0.1 (2026-08-08) - dropped the fictional example projects from the precedence note
81
+
82
+ - 1.0.0 (2026-06-19) - initial version, generalized from a project-specific daily-improve workflow (metrics/scripts coupling removed)
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: database-schema-evolution
3
3
  description: Use when renaming or reshaping tables/columns, when a schema migration is risky, when a schema change touches many usages across the code, or when a zero-downtime migration is required - "migrate this schema", "migre ce schéma", "rename this column", "renomme cette colonne", "zero-downtime migration".
4
- version: 1.0.0
4
+ version: 1.0.1
5
5
  metadata:
6
- last-reviewed: 2026-06-19
6
+ last-reviewed: 2026-08-08
7
7
  category: process
8
8
  ---
9
9
 
10
10
  # Database Schema Evolution - evolve a schema with no breakage or downtime
11
11
 
12
- > If the current repo has a project-specific migration skill (e.g. acme-app → `bulk-db-migration`), it wins - it knows the SQL engine, the migration tool, the commands and the project's CI gates.
12
+ > If the current repo has a project-specific migration skill, it wins - it knows the SQL engine, the migration tool, the commands and the project's CI gates.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -104,4 +104,6 @@ A missing box = do not apply in production.
104
104
 
105
105
  ## Changelog
106
106
 
107
- - 1.0.0 (2026-06-19) - initial version; provider-agnostic generalization of `bulk-db-migration` (acme-app) into a zero-downtime expand-contract protocol
107
+ - 1.0.1 (2026-08-08) - dropped the fictional example projects from the precedence note
108
+
109
+ - 1.0.0 (2026-06-19) - initial version; provider-agnostic generalization of a project-specific `bulk-db-migration` workflow into a zero-downtime expand-contract protocol
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: ddd-backend-implementation
3
3
  description: Use when implementing a backend feature in DDD layers, deciding where business logic / validation / I-O belongs during implementation, respecting the dependency direction toward the domain, or splitting commands from queries (CQRS). Use AFTER the model is designed, DURING implementation - "implement this backend feature", "implémente cette feature backend", "code these DDD layers", "implémente les couches DDD".
4
- version: 1.0.0
4
+ version: 1.0.1
5
5
  metadata:
6
- last-reviewed: 2026-06-19
6
+ last-reviewed: 2026-08-08
7
7
  category: feature
8
8
  ---
9
9
 
10
10
  # DDD Backend Implementation - build a feature layer by layer
11
11
 
12
- > If the current repo has a specific implementation skill (e.g. acme-app → `feature-implementation-rust-axum`), it wins - it knows the stack, the paths and the project commands.
12
+ > If the current repo has a specific implementation skill, it wins - it knows the stack, the paths and the project commands.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -92,4 +92,6 @@ Implement in this order, never the reverse, never a short-circuit. Test each lay
92
92
 
93
93
  ## Changelog
94
94
 
95
+ - 1.0.1 (2026-08-08) - dropped the fictional example projects from the precedence note
96
+
95
97
  - 1.0.0 (2026-06-19) - initial generic version extracted from a project workflow, decoupled from any stack and any tracker
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: design-system-component-lifecycle
3
3
  description: Use when creating or extending a design system component, defining a reusable component contract (props/slots/events, tokens), enforcing token usage over hardcoded values, or avoiding duplicated one-off components - "add a component", "a component is needed for", "ajoute un composant", "il manque un composant pour", element/pattern repeated across pages.
4
- version: 1.0.0
4
+ version: 1.0.1
5
5
  metadata:
6
- last-reviewed: 2026-06-19
6
+ last-reviewed: 2026-08-08
7
7
  category: frontend
8
8
  ---
9
9
 
10
10
  # Design system component lifecycle - decision → contract → enforcement
11
11
 
12
- > If the current repo has an equivalent skill (e.g. acme-app → `design-system-extension`), it wins - it knows the component prefix, the lint rules, and the project's audit specs.
12
+ > If the current repo has an equivalent skill, it wins - it knows the component prefix, the lint rules, and the project's audit specs.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -94,4 +94,6 @@ A DS component is not just a view file: it is a file **+ its enforcement**. With
94
94
 
95
95
  ## Changelog
96
96
 
97
- - 1.0.0 (2026-06-19) - initial version generalized from acme-app's design-system-extension workflow
97
+ - 1.0.1 (2026-08-08) - dropped the fictional example projects from the precedence note
98
+
99
+ - 1.0.0 (2026-06-19) - initial version generalized from a project-specific design-system-extension workflow
@@ -1,15 +1,15 @@
1
1
  ---
2
2
  name: detection-sweep
3
3
  description: Use when asked to check the whole project and report problems - "check the whole project", "detect the problems", "run a sweep", "vérifie tout le projet", "détecte les problèmes", "lance un sweep", periodic health check of a codebase, before a release audit.
4
- version: 1.0.2
4
+ version: 1.0.4
5
5
  metadata:
6
- last-reviewed: 2026-07-20
6
+ last-reviewed: 2026-08-08
7
7
  category: audit
8
8
  ---
9
9
 
10
10
  # Detection Sweep - detect, ticket, fix nothing
11
11
 
12
- > If the current repo has a specific sweep skill (e.g. acme-app → `test-sweep`), it wins - it knows the project's blocks and tracker.
12
+ > If the current repo has a specific sweep skill, it wins - it knows the project's blocks and tracker.
13
13
 
14
14
  ## This skill vs. others
15
15
 
@@ -86,6 +86,10 @@ Workflow directives for the sweep as a whole (state them when invoking the skill
86
86
 
87
87
  ## Changelog
88
88
 
89
+ - 1.0.4 (2026-08-08) - dropped the fictional example projects from the precedence note
90
+
91
+ - 1.0.3 (2026-08-08) - sweep.ts iterates instead of returning a value from forEach
92
+
89
93
  - 1.0.2 (2026-07-20) - co-located test procedure for sweep.ts (scripts/sweep.test.ts)
90
94
 
91
95
  - 1.0.1 (2026-07-20) - workflow directives clarified as skill options, not sweep.ts flags
@@ -70,11 +70,11 @@ section("Potential secrets (check)");
70
70
  row("Secret patterns", /AKIA[0-9A-Z]{16}|-----BEGIN [A-Z ]*PRIVATE KEY-----|sk_live_|glpat-|ghp_/);
71
71
 
72
72
  section(`Large files (> ${BIG_FILE_LINES} lines)`);
73
- files
73
+ const bigFiles = files
74
74
  .map(({ f, lines }) => ({ f, n: lines.length }))
75
75
  .filter(({ n }) => n > BIG_FILE_LINES)
76
76
  .sort((a, b) => b.n - a.n)
77
- .slice(0, 15)
78
- .forEach(({ f, n }) => console.log(`${String(n).padStart(6)} ${f}`));
77
+ .slice(0, 15);
78
+ for (const { f, n } of bigFiles) console.log(`${String(n).padStart(6)} ${f}`);
79
79
 
80
80
  console.log("\n→ Triage these signals: 1 ticket per root cause, not 1 per occurrence (see the detection-sweep skill).");
@@ -0,0 +1,44 @@
1
+ # domain-glossary
2
+
3
+ Fixes the vocabulary of a codebase in a `GLOSSARY.md` the code travels with, so
4
+ one concept keeps one name, for the people reading it and for the agent naming
5
+ the next module.
6
+
7
+ ## What it is for
8
+
9
+ You have three names for the same thing (`user`, `member`, `account`), or one
10
+ name for two things (an `Order` in sales, an `Order` in a sort), and every new
11
+ piece of code picks whichever the author saw last. Or you are onboarding onto a
12
+ domain and the words themselves are the obstacle.
13
+
14
+ `SKILL.md` is the source of truth for the protocol: harvest the terms from the
15
+ code rather than from memory, separate synonyms from homonyms, decide one name
16
+ per concept, anchor each entry to a type/table/route, and record what was
17
+ rejected and why.
18
+
19
+ ## What it is not for
20
+
21
+ - Designing the aggregates and invariants → `domain-modeling-design`
22
+ - Preserving a *decision* rather than a *term* → `recording-decisions`
23
+ - Finding the call sites of an existing component → `frontend-spec-call-site-audit`
24
+
25
+ ## Why the rejected terms matter
26
+
27
+ The property that separates a glossary that holds from a list of definitions is
28
+ the "we do not say" line. A definition tells you what `tenant` means; the
29
+ rejection tells you that `organization` was considered, dropped, and why, which
30
+ is what stops the next reader from reopening the debate and landing elsewhere.
31
+ It is also what makes a search for the wrong word arrive at the right entry.
32
+
33
+ ## Output
34
+
35
+ A `GLOSSARY.md` at the repository root, ordered for lookup, where each entry
36
+ names at least one place the term is real in the code, and unsettled terms are
37
+ marked provisional rather than dressed up as decided.
38
+
39
+ ## How it is verified
40
+
41
+ `eval.yaml` plays it against the `flawed-app` fixture and gates on the file
42
+ being produced, then has a judge check the properties that are not greppable:
43
+ entries anchored to real code, rejected terms recorded, no invented vocabulary
44
+ the codebase does not use.