repo-standards
Skill2 starsChanged 4 months agoMITView on GitHub
Use when auditing or polishing a repository to Tamir Cohen standards — README badges, Makefile install/update/uninstall, docs tree, CI/CD, changelog and versioning policy, branch protection, employer IP scan, repo hygiene, multi-agent setup. Triggers: repo standards, polish this repo, prepare this for GitHub, world-class repo, publish-ready, scan employer IP, fix repo hygiene, standards audit.
- Commits and pushes
3 other projects use a version of this.
Adopted by
Most recently taken up by
- itsryanarmani/skillstheir own version, first seen Nov 8, 2026
- pooriaarab/skillstheir own version, first seen Nov 7, 2026
- ssv445/claude-skillstheir own version, first seen Oct 13, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ssv445/claude-skills★ 2same name
- itsryanarmani/skills★ 1same name
- pooriaarab/skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/commit-conventions.mdcCursor rule
- .cursor/rules/cross-platform-handoff.mdcCursor rule
- .cursor/rules/dev-files-workspace.mdcCursor rule
- .cursor/rules/documentation-standards.mdcCursor rule
- .cursor/rules/gh-cli-preference.mdcCursor rule
- .cursor/rules/github-repository-policy.mdcCursor rule
- .cursor/rules/git-worktree-agent-workflow.mdcCursor rule
- .cursor/rules/hooks-guide.mdcCursor rule
- .cursor/rules/plugin-structure.mdcCursor rule
- .cursor/rules/plugin-version-bump.mdcCursor rule
- .cursor/rules/skill-frontmatter.mdcCursor rule
- .cursor/rules/skill-quality-standards.mdcCursor rule
- .cursor/rules/skills-guide.mdcCursor rule
- .cursor/rules/user-facing-script-standards.mdcCursor rule
- run-tamirs-superpowersSkill
- field-notebook-uiSkill
- diagnose-refusalSkill
- targeted-debugSkill
- decisionSkill
- deliver-devSkill
- diagnose-objectiveSkill
- orchestrate-devSkill
- plan-devSkill
- pr-devSkill
- start-devSkill
- switch-devSkill
- worker-devSkill
- changelog-reviewSkill
- dark-terminal-docSkill
- docs-reviewSkill
- platform-syncSkill
- mcp-builderSkill
- mcp-paginationSkill
- cleanupSkill
- github-policySkill
- multi-agent-repoSkill
- repo-scaffoldSkill
- capture-configSkill
- find-skillSkill
- notify-setupSkill
- retroSkill
- session-reportSkill
- skill-creatorSkill
- usage-captureSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
17 rules. 0 are common, 6 are distinctive, and 11 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
11
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 93
Run inventory + gap scoring before rubric walk (review) or plan grouping.
- Very specific: line 95
Write reports only to paths in mode-contracts.md.
- Very specific: line 127
Read references/standards-rubric.md.
- Very specific: line 128
Start findings from $GAPS JSON (profile: $CONTRACT_PROFILE).
- Very specific: line 131
Read-only docs pass: summarize README + docs/ issues without calling Skill("docs-review") (it mutates files).
- Distinctive: line 132
When multi-platform, walk Per-target parity (V-layer) for every declared target and record V-01…V-05 gaps as P1.
- Very specific: line 134
Write $REVIEW_PATH from templates/review-report.md.tmpl.
- Distinctive: line 165
Stop: No implementation edits in review mode.
- Distinctive: line 175
If no review doc, run review mode first.
- Very specific: line 176
Read review ($DOC_PATH, user path, or latest repo-standards-review-*.md).
- Distinctive: line 198
If no plan doc, run plan mode first.
- Very specific: line 199
Read plan ($DOC_PATH, user path, or $PLAN_PATH).
- Very specific: line 200
Phase 0: Run ip-scan.sh; fix hits; re-scan until CLEAN.
- Very specific: line 237
Phase 6b (agents only): When multi-platform, run make platform-targets-sync, update platform-targets.json + README Row 3 + …
- Very specific: line 238
Phase 7: Run make repo-standards-gate when multi-platform (or make agent-polish-gate + assert-contract --manifests-only on release PRs …
- Very specific: line 240
Commit in logical chunks; push.
- Distinctive: line 280
IP scan clean: before final PR.
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
repo-standards
Audit, plan, and implement Tamir Cohen repo standards: README + docs tree, GitHub CI/CD, branch governance, employer-IP clean, repo hygiene, and multi-agent support (via multi-agent-repo). Auto-detects app-gold vs plugin-gold (agent-kit repos).
User guide (agent-kit): docs/user/agent-kit.md
Why this skill exists
Publishing or maintaining a repo without a unified checklist leaks employer IP, ships thin READMEs, and leaves agents without AGENTS.md. This skill runs review → plan → polish so gaps are visible, phased, and land on a PR branch — without auto-creating remotes or merging.
Supporting files
| Path | When to read |
../_contract/README.md | Contract change workflow; canonical paths |
../_contract/standards-contract.json | Machine contract (app-gold profile) |
../_contract/templates/INDEX.md | Polish phase 1–4 templates |
references/mode-contracts.md | Parse args; stop conditions |
references/standards-rubric.md | Pointer → _contract/standards-rubric.md |
references/polish-phases.md | Polish implementation order |
references/delegation.md | Skill() prompts for child skills |
references/plugin-review.md | Agent-kit / plugin-gold manual review axes |
../_contract/references/readme-badges.md | Badge rows and markup rules, Makefile lifecycle, multi-target README |
../_contract/references/readme-banner.md | Hero banner art direction, quality bar, footer |
../_contract/references/versioning-policy.md | Semver, tagging, changelog enforcement |
../../../config/github/repository-policy.json | Canonical GitHub repository policy — rulesets, required contexts, Actions concurrency. Never restate its content; read it. |
../../../scripts/github-policy.sh | audit / plan / apply / verify for branch governance (S4-02…S4-14) |
../../../scripts/github-labels.sh | audit / plan / apply for the canonical label set (S3-05); --prune is the only path that deletes |
scripts/parse-mode-args.sh | Mode/target/doc_path parsing |
scripts/standards-inventory.sh | Re-export → _contract/scripts/ |
scripts/score-contract-gaps.sh | Merged standards + multi-agent gaps |
scripts/assert-contract.sh | Polish exit gate (app-gold P1/P2/P3 = 0) |
scripts/ip-scan.sh | Employer IP scan |
templates/*.md.tmpl | Report, plan, PR body |
Required execution flow
- Parse with
parse-mode-args.sh. - Run inventory + gap scoring before rubric walk (review) or plan grouping.
- Route to one mode; plan/polish may chain review in the same turn.
- Write reports only to paths in
mode-contracts.md.
Parse input
SKILL_DIR="$CLAUDE_SKILL_DIR"
CONTRACT_ROOT="$(cd "$SKILL_DIR/../_contract" && pwd)"
PARSED="$(bash "$SKILL_DIR/scripts/parse-mode-args.sh" $ARGUMENTS)"
MODE="$(echo "$PARSED" | jq -r '.mode')"
TARGET_ROOT="$(echo "$PARSED" | jq -r '.target')"
DOC_PATH="$(echo "$PARSED" | jq -r '.doc_path // empty')"
CONSTRAINTS="$(echo "$PARSED" | jq -r '.constraints')"
DATE="$(date +%Y-%m-%d)"
CONTRACT_PROFILE="$(bash "$CONTRACT_ROOT/scripts/detect-contract-profile.sh" "$TARGET_ROOT")"
INVENTORY="$(bash "$SKILL_DIR/scripts/standards-inventory.sh" "$TARGET_ROOT")"
GAPS="$(bash "$SKILL_DIR/scripts/score-contract-gaps.sh" "$TARGET_ROOT" "$CONTRACT_PROFILE")"
IP_SCAN="$(bash "$SKILL_DIR/scripts/ip-scan.sh" "$TARGET_ROOT" 2>&1 || true)"
PLUGIN_ROOT="$(cd "$CONTRACT_ROOT/../../.." && pwd)"
POLICY_CLI="$PLUGIN_ROOT/scripts/github-policy.sh"
REPO_SLUG="$(git -C "$TARGET_ROOT" remote get-url origin 2>/dev/null | sed -E 's#^.*github\.com[:/]##; s#\.git$##' || true)"
REVIEW_PATH="$TARGET_ROOT/docs/engineering/repo-standards-review-$DATE.md"
PLAN_PATH="$TARGET_ROOT/docs/engineering/repo-standards-plan-$DATE.md"Mode: review (read-only)
Goal: Unified gap report (standards S1–S7 + multi-agent S8 + E/V feature equivalence). No repo edits except the report file.
Steps
- Read
references/standards-rubric.md. If$CONTRACT_PROFILEisplugin-gold, also readreferences/plugin-review.md. - Start findings from
$GAPSJSON (profile:$CONTRACT_PROFILE); walk rubric for qualitative gaps (README prose, doc content). - Include
$IP_SCANsummary; flag S7-01 P1 if not CLEAN. cd "$TARGET_ROOT"thenSkill("multi-agent-repo")usingreferences/delegation.mdreview prompt. Append child summary to report — do not duplicate full child report.- Read-only docs pass: summarize README +
docs/**issues without callingSkill("docs-review")(it mutates files). - When multi-platform, walk Per-target parity (V-layer) for every declared target and record V-01…V-05 gaps as P1.
mkdir -p "$TARGET_ROOT/docs/engineering"- Write
$REVIEW_PATHfromtemplates/review-report.md.tmpl.
Report structure
# Repo standards review — [repo name]
## Executive summary
## Severity summary
## Standards gaps (S1–S7 + PK* if plugin-gold)
## Plugin / agent-kit appendix (if plugin-gold)
## Employer IP scan
## GitHub repository policy
## Multi-agent appendix
## Feature equivalence appendix (E-layer)
## Platform targets appendix (V-layer)
## Docs read-only notes
## Inventory appendix (JSON)
## Next steps## GitHub repository policy is populated from $INVENTORY's branch_governance block and, when $REPO_SLUG is non-empty and gh is authenticated, bash "$POLICY_CLI" audit --repo "$REPO_SLUG". Record, in this order:
- Which mechanism governs the default branch — rulesets, classic protection, or nothing (
branch_governance.source). - Per-ruleset compliance as the audit reports it, plus any CONFLICT the audit refuses to resolve.
strict_required_status_checks_policy— its literal value, because S4-09 is the one setting that must never silently flip.- Legacy classic protection as a migration item. Absent is the healthy state on a rulesets-governed repo and is never a finding.
- Actions concurrency findings in both directions: a cancellable PR-validation workflow missing the block, and a stateful workflow that wrongly has cancellation on.
- Labels (S3-05) from
$INVENTORY'sgithub.labelsblock: how many canonical labels are missing (name them) and how many drifted, and whether issue templates exist (S3-06,github.issue_templates). Whengithub.labels.checkedisfalsethe set could not be read — say so and score no S3-05 gap. Citeconfig/github/labels.jsonfor the set; never list its labels in the report.
When governance could not be read (branch_governance.readable is false — no gh, no auth, or no permission), say so plainly and score no S4 gaps. An unread control is unknown, not broken. Never copy rule values, ruleset names, or required-context lists out of config/github/repository-policy.json into the report — cite the file.
Stop. No implementation edits in review mode.
Mode: plan
Goal: Phased remediation from review findings.
Steps
- If no review doc, run review mode first.
- Read review (
$DOC_PATH, user path, or latestrepo-standards-review-*.md). - Group P1/P2 into phases 0–7 per
references/polish-phases.md. - Note
Skill("multi-agent-repo")for phase 5 (add--constraints pluginwhen$CONTRACT_PROFILE=plugin-gold) anddocs-review/changelog-reviewfor phase 6. - Write
$PLAN_PATHfromtemplates/remediation-plan.md.tmpl. - Present plan summary.
Stop unless mode is polish.
Mode: polish
Goal: Implement plan on feat/repo-standards-setup; open PR. Never merge. Never gh repo create.
Preconditions
- Git repo at
$TARGET_ROOT ghauthenticated- Warn if dirty working tree
Steps
- If no plan doc, run plan mode first.
- Read plan (
$DOC_PATH, user path, or$PLAN_PATH). - Phase 0: Run
ip-scan.sh; fix hits; re-scan until CLEAN. User must acknowledge findings before large edits if first polish run. - Create branch:
cd "$TARGET_ROOT"
git checkout -b feat/repo-standards-setup 2>/dev/null || git checkout -b "feat/repo-standards-setup-$(date +%s)"Phases 1–4: Implement per plan using
$CONTRACT_ROOT/templates/(seeINDEX.md). Phase 4 (branch governance) — after the CI workflow is on the default branch:bash "$CONTRACT_ROOT/scripts/enable-repo-merge-settings.sh" bash "$POLICY_CLI" plan --repo "$REPO_SLUG" # diff only, writes nothing bash "$POLICY_CLI" apply --repo "$REPO_SLUG" # confirms each change at the TTYgithub-policy.shreplacedensure-branch-protection.sh, which read and wrote classicbranches/*/protection— an endpoint that 404s on a repository correctly governed by rulesets, so it reported protected repos as unprotected. The old script survives only as a deprecating shim onto these verbs.Rulesets are authoritative; classic protection is a legacy migration item, reported and never written, and its absence is not a gap. Every rule, required context, and enforcement value comes from
config/github/repository-policy.json— do not restate any of it here or in the report.planwhen the user asked to audit only, or asked to skip applying rules (this is what--verify-onlyused to mean).auditfor the read-only compliance answer with no remediation diff.applynever writes without a confirmation, refuses any change that would make the repo less protected than it is today, and prints the plan instead of writing when there is no TTY.strict_required_status_checks_policymust stayfalse(S4-09, P1). With it on, every merge marks every other open branch out of date and the one-objective/one-PR flow stalls behind a serial rebase queue.
Labels (S3-05, S3-06) — in the same phase, right after the rulesets:
bash "$PLUGIN_ROOT/scripts/github-labels.sh" plan --repo "$REPO_SLUG" # diff only, writes nothing bash "$PLUGIN_ROOT/scripts/github-labels.sh" apply --repo "$REPO_SLUG" # creates + updates, confirms at the TTYThe set is
config/github/labels.jsonplus oneagent:<platform>per registry platform; do not restate it.applynever deletes a label unless--pruneis typed — leave extras alone unless the user asked to prune. For S3-06, add.github/ISSUE_TEMPLATE/*.ymlforms that label only with names the set provides (check-github-labels.shholds this repo's templates to that). README branding (phase 1): S1-05 and S1-11..S1-14 are all fixed here, and all five are verified bybash "$CONTRACT_ROOT/scripts/check-readme-branding.sh" "$TARGET_ROOT"before the phase closes.- S1-11 anchor form — collapse every
<a>that wraps a badge<img>onto one line:<a href="..."><img ... /></a>. The newline and indent in the broken form are link text; GitHub renders them as the underlined gap between badges. Do not reformat them back. - S1-12 header emoji — remove every emoji above the first
##heading (banner, badge rows, H1, tagline). Body prose is untouched. - S1-13 badge versions — re-derive each AI-target badge from
docs/engineering/build-and-release/platform-targets.jsontargets.<key>.validated_against. Never carry a version over from another repo or from the reference doc's example. - S1-05 / S1-14 banner — if absent or if it fails the quality bar, produce a real one per
../_contract/references/readme-banner.md: a motif drawn from what the project does, three depth planes, a gradient, a faint substrate, wordmark left.assets/banner.png|jpg|webp|svgall count; a raster is preferred when you can render one. The bar is mechanical — ≥16 non-text shapes, ≤3<text>, ≥5 shapes per text element, at least one gradient/filter/mask/opacity, a<title>+<desc>naming the motif, zero emoji codepoints. A dark rectangle with the repo name centred in it is the failure this check exists for. Reference it as the first line of README.md inside<p align="center">, and close the README with the one-line text footerMIT © [Tamir Cohen](https://github.com/Tamircohen28).
- Phase 5:
Skill("multi-agent-repo")perreferences/delegation.mdon the same branch (include feature equivalence + platform targets). - Phase 6:
Skill("docs-review"); if plugin or agent-kit repo,Skill("changelog-review"). Fix all P1 findings. - Phase 6b (agents only): When multi-platform, run
make platform-targets-sync, updateplatform-targets.json+ README Row 3 +platform-targets.md, thenmake platform-targets-assert. Close every V-01…V-05 gap from the review in this phase — a declared target with a missing artifact must either be completed or dropped fromsupported_targets, never left half-supported. - Phase 7: Run
make repo-standards-gatewhen multi-platform (ormake agent-polish-gate+assert-contract --manifests-onlyon release PRs before the tag exists). P1/P2/P3 must be 0. $REVIEW_PATHand$PLAN_PATHare session scratch notes, not deliverables — remove them from the branch before the final commit so they never ship in the PR:git rm --ignore-unmatch "$REVIEW_PATH" "$PLAN_PATH"(or plainrmif untracked).- Commit in logical chunks; push;
gh pr createwithtemplates/pr-body.md.tmpl. - Print PR URL.
Stop at PR.
Per-target parity (V-layer)
A repo that declares support for a target owes that target a full set of artifacts. Partial support is worse than no support: the target appears in the README, users install against it, and the gaps surface as "the plugin is broken" rather than "this target was never finished".
For every key in platform-targets.json → supported_targets, confirm all five exist. Report a missing one as P1:
| # | Artifact | Failure mode when missing |
| V-01 | Manifest or config for the target | Target cannot load the content at all |
| V-02 | docs/user/install/<target>.md, linked from the install README | Users have no documented path in |
| V-03 | targets.<key> entry with validated_against, verified_on, verification_method, install_doc | Version support is a guess; nothing can assert staleness |
| V-04 | A per-target sub-skill under the platform-sync umbrella | /platform-sync skips the target silently and reports success — reads as "no improvements found" |
| V-05 | The target named in README.md, AGENTS.md and CLAUDE.md | Invisible to users and to other agents |
| V-06 | A core/capabilities/platforms.json entry with an explicit status for every capability key | Skills assume capabilities the target lacks instead of degrading; gaps are re-litigated every audit |
A target whose validated_against is "unknown" is declared but not yet validated. V-02, V-04 and V-05 degrade to warnings for it, and it carries no README badge — that is the honest state, not a defect. It becomes a hard failure the moment a real version is recorded, so a declared target cannot sit unvalidated behind a green build once someone claims to have run it.
Two failure modes to check for specifically, because both fail quietly:
- Marketplace declaration shape. Claude Code's
extraKnownMarketplacesis a record keyed by marketplace name, never an array. An array is dropped with no error and no warning, and a valid global~/.claude/settings.jsoncan mask the broken project-level file for months. Nested form issource: {source, repo}(GitHub) orsource: {source, url}(git); there is nosourceUrlfield. Verify withclaude doctor. Since Claude Code 2.1.232,additionalMarketplacesis accepted as a friendlier alias (andallowedMarketplacesforstrictKnownMarketplaces) — same record shape, same silent-drop trap for arrays; keepextraKnownMarketplacesin files that must load on older versions. - Capability assumptions across targets. Do not recommend a fix that assumes a capability the target lacks. Look the answer up in
core/capabilities/platforms.json— the capability registry is the only source for this, and it records a status for all 19 capability keys on every target. Read the status out of the registry at audit time — do not carry one in your head or quote one from this file. Statuses move as targets are re-measured: OpenCode'shooksand Gemini'sskillsandsubagentshave each changed value during a single release cycle, and any prose that had pinned them was wrong within the day. Record a newly discovered gap in the registry, then runbash scripts/check-platform-targets.sh . --sync-capabilitiesto refresh the derivedcapabilities/capability_gapsmirror inplatform-targets.json. Never hand-edit that mirror and never restate a status in prose:make check-feature-equivalencefails the build when two views of the platform set disagree.
make check-doc-claims enforces V-02, V-03, and V-05 — and computes the skill count and the supported-target count from the filesystem, so a stale "28 skills" or "four supported targets" in any Markdown or manifest fails CI rather than aging quietly. make check-platform-targets enforces V-04 and the derived capability mirror; make check-feature-equivalence enforces V-06 and registry agreement; make check-marketplace-schema enforces the record shape. All run inside make validate. Use bash scripts/check-doc-claims.sh --expected to print the numbers the docs must state.
Agent execution rule
Agents run make repo-standards-gate during repo-standards polish and via start-dev / pr-dev (run-pre-pr-gates.sh) before every push/PR — never instruct the user to run bash scripts/check-*.sh directly.
Hard rules
- Never
runs-on: [self-hosted]in generated CI. - Never push to GitHub new repo from this skill — PR on existing remote only.
- Never merge the PR from this skill.
- IP scan clean before final PR.
- Apply all P1 standards + multi-agent gaps before PR.
- No half-supported targets — every key in
supported_targetscarries all five V-layer artifacts, or it comes out of the list. - AGENTS.md canonical — delegate multi-agent file generation to
multi-agent-repo.
Relationship to other skills
| Skill | When to use instead |
repo-scaffold | Brand-new repo from scratch |
multi-agent-repo | Multi-agent setup only, no full standards pass |
pr-dev | Drive the standards PR to merge after polish |
Example invocations
/repo-standards
/repo-standards review ../my-app
/repo-standards plan
/repo-standards polish
/repo-standards polish . -- skip branch protection for nowDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

