CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pre-release-review

Run a read-only pre-release review for deploy readiness, migrations, config, secrets, rollout order, rollback risk, and launch blockers.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

85%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 well-structured, highly actionable instruction-only skill: read-only commands are concrete, the workflow is sequenced with explicit checkpoints and fallback handling, and detail is properly deferred to two real, clearly-signaled reference files. The only weakness is mild redundancy between the body and the report template.

DimensionReasoningScore

Conciseness

The body is dense and assumes Claude's competence — no concept explanations, just rules, commands, and procedures — but sections like "Findings versus verification limits" and "Limitations" repeat material already in references/report-template.md and the non-negotiable rules, leaving minor trimming opportunities that fit anchor 4.

4 / 5

Actionability

Guidance is mostly executable: a copy-paste block of read-only git/rg commands, an ordered scope-selection decision procedure, exact conclusion enums (BLOCKED, NEEDS_CONFIRMATION, NO_BLOCKER_FOUND), and concrete owner-inference commands, with only minor gaps such as the generic "rg -n \"<pattern>\"" placeholder and no worked example.

4 / 5

Workflow Clarity

The 7-step workflow is clearly sequenced with explicit checkpoints — confirm range/dirty state before judging risk, classify findings with the template, cite evidence per finding — and includes error-recovery loops (PR fetch failure asks for a local range, missing tags fall back to the latest 5 commits with an explicit warning) plus a checklist for the complex process, matching anchor 5. The skill is strictly read-only, so the destructive/batch validation cap does not apply.

5 / 5

Progressive Disclosure

Both referenced files (references/checklist.md and references/report-template.md) exist, are one level deep, and are clearly signaled in a "Required references" section that states when to read each; the bulk detail (checklist categories, report format) is appropriately split out of the overview body, matching anchor 5.

5 / 5

Total

18

/

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 clear, specific description with good natural trigger terms and a well-carved niche, but it lacks an explicit "Use when..." clause, capping completeness. Adding trigger guidance with synonyms like "release audit" or "go-live review" would raise it to the top band.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks for a release audit, go-live review, or deploy readiness check before publishing a tag, merging a release branch, or deploying production."

Add natural synonyms such as "release audit", "go-live review", and "ship readiness" to broaden trigger-term coverage.

Mention the deliverable (a prioritized read-only risk report) so the "what" covers the output as well as the review areas.

DimensionReasoningScore

Specificity

The description names the domain and enumerates concrete review targets — "deploy readiness, migrations, config, secrets, rollout order, rollback risk, and launch blockers" — plus the read-only constraint, which goes beyond the 1-2 actions of anchor 3 but stops short of anchor 5's fully comprehensive action coverage (e.g., it never mentions producing a risk report).

4 / 5

Completeness

The "what" is clear (run a read-only pre-release review across the listed areas) but there is no "Use when..." clause or equivalent explicit trigger guidance — timing is only weakly implied by "pre-release" — which the rubric caps at 3.

3 / 5

Trigger Term Quality

Natural phrases like "pre-release review", "deploy readiness", "rollback risk", and "launch blockers" are present and would be said by users needing this skill, but common synonyms such as "release audit", "go-live", or "ship readiness" are missing, matching anchor 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

The deploy-readiness/release niche with triggers like "rollback risk" and "launch blockers" is mostly distinct, but it has minor overlap risk with closely related general code-review and security-review skills, fitting anchor 4 rather than anchor 5's minimal-conflict bar.

4 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

BigSimmo/Communication

Path

.agents/skills/pre-release-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.