CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

release-readiness-review

Two-phase pattern for release readiness: Phase 1 audits build/vet/test/security/docs → report gaps. Phase 2 closes gaps and tags the release.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/release-readiness-review/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

68%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A tight, command-driven two-phase release workflow with good structure and mostly executable guidance. Its main weakness is validation ordering: gap closure flows directly into tagging without an explicit re-audit checkpoint, and Docker/smoke verification is placed after the release tag is pushed.

Suggestions

Add an explicit pre-tag verification step in Phase 2 (e.g., 'Re-run the Phase 1 checklist and only tag when all items pass') and move Docker verification/smoke-test before 'git tag'/'git push', creating a validate-fix-retry loop for this batch/outward-facing operation.

Make the Security and Docker checklist items actionable — provide the command or inspection method for checking 'session auth, BOLA, CSRF, CSP, XSS escaping, SSRF protection' and 'Dockerfile correctness' rather than listing bare topic names.

Resolve the placeholder paths in Related Files (e.g., 'docs/plans/YYYY-MM-DD-release-and-gap-closure-design.md') to literal filenames or describe how to locate them.

DimensionReasoningScore

Conciseness

The body is lean — a checklist with inline commands and no explanations of concepts Claude already knows. Minor padding remains: the Overview duplicates the frontmatter description verbatim and the Related Files section adds marginal value. Anchor 5 ('every token earns its place') is not quite met.

4 / 5

Actionability

Highly concrete with exact executable commands ('go build ./cmd/server ./cmd/worker ./cmd/cli ./cmd/agent', 'go vet ./...', 'govulncheck ./...', 'git tag -a v0.0.1', 'docker compose build netrunner'). Gaps: 'Security: session auth, BOLA, CSRF, CSP, XSS escaping, SSRF protection' and 'Dockerfile correctness' name topics without any command or method to check them, and 'Typical Gaps' items are hints rather than steps.

4 / 5

Workflow Clarity

The two-phase sequence is clear (audit with 'Do NOT fix anything in this phase', gap report, then closure and tagging), but the pre-tag feedback loop is missing: Phase 2 says 'Implement all gaps found in Phase 1, then tag the release' with no explicit re-verification step, and Docker verification/smoke-test appears after the tag is pushed. Because tagging and pushing a release is a batch/outward-facing operation, the missing validation gate caps this at 3 per the rubric's batch-operations guidance.

3 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent) and the ~65-line body is self-contained with clear sections — appropriate for a skill this size. Minor organization gaps: 'Related Files' lists placeholder paths ('docs/plans/YYYY-MM-DD-release-and-gap-closure-design.md') that do not resolve literally, and referenced paths like './scripts/smoke-test.sh' are repo files rather than clearly signaled skill references.

4 / 5

Total

15

/

20

Passed

Description

66%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A concise, concrete description that clearly states what the skill does across both phases, with good trigger terms and low conflict risk. Its main deficiency is the complete absence of 'when to use it' guidance, which caps completeness.

Suggestions

Add an explicit trigger clause, e.g., 'Use when preparing to ship, tag, or cut a release of NetRunner, when the user asks if the codebase is release-ready, or before creating a release PR.'

Include natural synonyms users would say — 'ship', 'prepare a release', 'pre-release checks' — alongside 'release readiness' to broaden trigger coverage.

Optionally mention the CI/Docker checks the body covers (e.g., 'audits build/vet/test/vulnerabilities/CI/Docker/docs') for fuller capability coverage.

DimensionReasoningScore

Specificity

Names the domain (release readiness) and several concrete actions — 'audits build/vet/test/security/docs', 'report gaps', 'closes gaps and tags the release'. Falls short of anchor 5's comprehensive coverage: the description omits CI/Docker coverage that the body actually audits, and 'report gaps' leaves the deliverable unspecified.

4 / 5

Completeness

The 'what' is explicit and clear (two phases: audit → gap report, then gap closure → tag), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because nothing in the description tells Claude when to invoke it.

3 / 5

Trigger Term Quality

Contains natural trigger terms users would say — 'release readiness', 'audit', 'gaps', 'tag the release'. A few natural terms are missing: common variations like 'ship', 'prepare a release', 'cut a release', 'pre-release checks', 'go live'. Not 3, since coverage is good rather than merely 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

'Release readiness' with the distinctive two-phase audit/tag pattern is a clear niche with minimal conflict risk. Minor overlap with general code-review, CI, or deployment skills keeps it from anchor 5.

4 / 5

Total

15

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

pvnkmnk/djinn-netrunner

Path

.agents/skills/release-readiness-review/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.