package-compliance-review
Review an APM package candidate for provenance, allowlist discipline, and publication safety.
Skill by JinkzEvol
Chalk Labs
Need help deploying package-compliance-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jinkzevol-package-compliance-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: security, writing
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/package-compliance-review
What's inside
- Skill name
package-compliance-review- Description
- Review an APM package candidate for provenance, allowlist discipline, and publication safety. Use when extracting, approving, or preparing Warp-derived package content.
- License
- Apache-2.0
- Instructions
- 45 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# package-compliance-review ## Purpose This skill reviews whether package content is ready to move from staging toward publication. It is intentionally focused on package hygiene rather than product behavior. Use it to verify that a candidate extraction is documented, scoped, and safe to publish. ## When to use - When new files are proposed for copying from the upstream Warp repo - When `docs/provenance-matrix.md` or `docs/allowlist.md` changes - Before changing package metadata such as `apm.yml`, `package.json`, notices, or README install instructions - Before creating a public GitHub repository or enabling npm publication ## Required inputs - The current `docs/provenance-matrix.md` - The current `docs/allowlist.md` - The current `docs/license-decision-log.md` - The files proposed for inclusion in `skills/` or other shipped paths ## Review workflow 1. Confirm every proposed shipped file has a provenance entry with a non-empty license classification. 2. Confirm every proposed copied file is explicitly allowed by `docs/allowlist.md`. 3. Confirm no file marked `unknown` is being treated as approved. 4. Confirm package metadata does not imply broader rights than the recorded provenance supports. 5. Call out any staging-only content that would need to be removed or relocated before public publication. ## Output Produce a short review with these sections: - `Status`: `ready`, `needs-work`, or `blocked` - `Findings`: concrete issues tied to files or docs - `Missing evidence`: anything still required before publication - `Next safe action`: the smallest compliant next step ## Guardrails - Do not approve content that lacks provenance. - Do not assume upstream Warp content is permissively licensed. - Do not recommend publication while `package.json` remains staging-only unless the recommendation explicitly says to keep it private.
From JinkzEvol/WarpSDLC, Apache-2.0.
More from JinkzEvol/WarpSDLC
- 0.476score
transplant-policy-pack
JinkzEvol
Generate policy and process scaffolding for a transplanted SDLC bundle by translating host bindings into PR, issue, review, and governance operating documents.
SkillCFreshness: CClaude Code +9 - 0.474score
research-brief
JinkzEvol
Produce a cited research brief from an approved tech spec at HOST_SPEC_ROOT and write research-brief.md to HOST_PLAN_DESTINATION with claims+citations and an…
SkillCFreshness: CClaude Code +9 - 0.468score
genesis
JinkzEvol
Use this skill before drafting or refactoring agentic primitives so design artifacts (diagrams, interface sketch, handoff packet) are produced first and…
SkillCFreshness: CClaude Code +9 - 0.467score
integration-test-video
JinkzEvol
Capture visual evidence for host integration tests only when the host provides HOST_VIDEO_CAPTURE and a compatible test harness; otherwise keep the sanitized…
SkillCFreshness: CClaude Code +9 - 0.467score
diagnose-ci-failures
JinkzEvol
Read CI failure evidence, categorize the failing slice, and emit a focused repair plan using HOST_CI_PROVIDER, HOST_LOG_ARTIFACTS, and HOST_PLAN_DESTINATION.
SkillCFreshness: CClaude Code +9 - 0.467score
fix-errors
JinkzEvol
Repair failing build, lint, typecheck, or test commands in the current host repo by reproducing the narrowest failure first using HOST_BUILD_COMMAND…
SkillCFreshness: CClaude Code +9 - 0.467score
implement-specs
JinkzEvol
Implement an approved PRODUCT.md and TECH.md pair while keeping specs, code, and HOST_VALIDATION_COMMAND evidence aligned in the same host-repo change set.
SkillCFreshness: CClaude Code +9 - 0.467score
review-pr
JinkzEvol
Review a checked-out pull request diff from local artifacts and produce structured review output using HOST_REVIEW_OUTPUT and HOST_REVIEW_SEVERITY instead of…
SkillCFreshness: CClaude Code +9 - 0.467score
spec-driven-implementation
JinkzEvol
Orchestrate a host-neutral spec-first workflow by creating PRODUCT.md before TECH.md when needed and then handing implementation to matching skills, using…
SkillCFreshness: CClaude Code +9 - 0.452score
sanitize-warp-sdlc
JinkzEvol
Regenerate the sanitized Warp SDLC layer by reading the Warp-only analysis docs, refreshing each approved -san skill, and preserving explicit placeholder…
SkillCFreshness: CClaude Code +9 - 0.442score
remove-feature-flag
JinkzEvol
Remove a stabilized host feature gate and the dead branches behind it while preserving placeholder comments for HOST_FEATURE_FLAG_SYSTEM and validation command.
SkillCFreshness: CClaude Code +9 - 0.442score
add-telemetry
JinkzEvol
Add host-neutral telemetry or instrumentation and preserve placeholder comments for the host event schema, HOST_TELEMETRY_SYSTEM, and privacy rules.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- May 6, 2026 (5 months ago)
- Last release
- May 6, 2026 (5 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- Apache-2.0
- Repository
- github.com/JinkzEvol/WarpSDLC
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from JinkzEvol
- 0.476score
transplant-policy-pack
JinkzEvol
Generate policy and process scaffolding for a transplanted SDLC bundle by translating host bindings into PR, issue, review, and governance operating documents.
SkillCFreshness: CClaude Code +9 - 0.474score
research-brief
JinkzEvol
Produce a cited research brief from an approved tech spec at HOST_SPEC_ROOT and write research-brief.md to HOST_PLAN_DESTINATION with claims+citations and an…
SkillCFreshness: CClaude Code +9 - 0.468score
genesis
JinkzEvol
Use this skill before drafting or refactoring agentic primitives so design artifacts (diagrams, interface sketch, handoff packet) are produced first and…
SkillCFreshness: CClaude Code +9 - 0.467score
implement-specs
JinkzEvol
Implement an approved PRODUCT.md and TECH.md pair while keeping specs, code, and HOST_VALIDATION_COMMAND evidence aligned in the same host-repo change set.
SkillCFreshness: CClaude Code +9 - 0.467score
diagnose-ci-failures
JinkzEvol
Read CI failure evidence, categorize the failing slice, and emit a focused repair plan using HOST_CI_PROVIDER, HOST_LOG_ARTIFACTS, and HOST_PLAN_DESTINATION.
SkillCFreshness: CClaude Code +9 - 0.467score
fix-errors
JinkzEvol
Repair failing build, lint, typecheck, or test commands in the current host repo by reproducing the narrowest failure first using HOST_BUILD_COMMAND…
SkillCFreshness: CClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get package-compliance-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
package-compliance-review skill. Agent Mart. https://agentmart.dev/skills/jinkzevol-package-compliance-review (last updated 2026-10-24)