CtrlK
BlogDocsLog inGet started
Tessl Logo

release

Coordinate a full Paperclip release across engineering verification, npm, GitHub, smoke testing, and announcement follow-up. Use when leadership asks to ship a release, not merely to discuss versioning.

70

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

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 highly actionable, well-sequenced release workflow with strong validation and failure-recovery loops. Its main weakness is progressive disclosure: it is a long single-file document with detailed API reference material inlined and no supporting reference files.

Suggestions

Move the Step 8 Cases HTTP/JSON reference and the local emergency/manual command block into a separate references/ file (e.g. RELEASE_CASES.md) and link to it from SKILL.md to reduce the monolith and improve progressive disclosure.

Remove the in-body Trigger section or collapse it into the frontmatter description to eliminate duplication and tighten conciseness.

Consolidate Preconditions, Inputs, and Step 0 into a single 'Before you start' section to cut overlapping prose without losing the validation checklist.

DimensionReasoningScore

Conciseness

The body is command- and example-driven and assumes Claude's intelligence (no explanations of npm, GitHub, or Docker), but the in-body Trigger section duplicates the frontmatter and Preconditions/Inputs/Step structure have some prose overlap, so a few passages could be trimmed.

4 / 5

Actionability

Provides copy-paste-ready commands ('./scripts/release.sh stable --date YYYY-MM-DD --print-version', smoke-test invocations, the verification gate), concrete file paths, git tag patterns, and full HTTP/JSON case-upsert examples covering the common cases.

5 / 5

Workflow Clarity

Steps 0–8 are explicitly sequenced with validation checkpoints (verify candidate SHA, run the gate, validate canary, smoke test, dry-run before live) and feedback loops for error recovery (stop-fix-rerun on smoke failure, rollback path, failure-handling section).

5 / 5

Progressive Disclosure

Sections are clearly headed and well-ordered, but the skill is a ~315-line monolith with no bundle files and no references to supporting material; sizable reference-style content (the Step 8 HTTP/JSON Cases block, local emergency commands) is inlined rather than split out, which fits the 3 anchor better than 4.

3 / 5

Total

17

/

20

Passed

Description

87%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 strong description that clearly states the release-coordination scope and gives an explicit, well-bounded trigger. Minor gaps in action specificity and trigger synonym coverage keep specificity and trigger_term_quality just below the top anchor.

DimensionReasoningScore

Specificity

Names the release domain and enumerates concrete surfaces ('engineering verification, npm, GitHub, smoke testing, and announcement follow-up'), but 'coordinate' is somewhat abstract and the listed items are surfaces rather than fully comprehensive concrete actions, so it sits below the 5 anchor.

4 / 5

Completeness

Explicitly answers both what ('Coordinate a full Paperclip release across engineering verification, npm, GitHub, smoke testing, and announcement follow-up') and when ('Use when leadership asks to ship a release, not merely to discuss versioning') with a concrete trigger phrase and a distinguishing negative boundary.

5 / 5

Trigger Term Quality

Includes a natural phrase users would say ('leadership asks to ship a release') plus the term 'release', giving good keyword coverage, but it omits common synonyms like 'cut a release' or 'promote a canary', so it does not reach comprehensive 5-level coverage.

4 / 5

Distinctiveness Conflict Risk

The 'Paperclip release' niche and the leadership-driven trigger plus the 'not merely to discuss versioning' boundary make it clearly distinguishable with minimal risk of firing for the wrong skill.

5 / 5

Total

18

/

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
paperclipai/paperclip
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.