CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cli-release

Release and recover first-party Composio CLI binaries through Build CLI Binaries, including automatic beta builds, promote-stable dispatches, beta-tag selection, asset and installation verification, and failed release recovery. Use when a contributor asks to build a CLI beta, publish or promote a stable CLI version, choose a release candidate, monitor a CLI release, or diagnose a failed CLI release. Do not use for TypeScript SDK Changesets releases or CLI source implementation.

Quality

97%

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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.

An exemplary orchestration-layer skill: a lean, project-fact-dense contract and sequenced execution path in SKILL.md, with all executable gh commands correctly pushed one level deep into a real, well-structured reference. Validation, confirmation, and recovery paths are all explicit, and nothing in the body wastes tokens on what Claude already knows.

DimensionReasoningScore

Conciseness

Every line carries project-specific facts Claude could not know — which workflow owns releases, the Changesets ignore rule, the development-sentinel versioning rule, the confirmation gate for production writes — with zero concept explanation or padding. This is the 5 anchor ('lean and efficient; every token earns its place'), not 4, since there is no over-explanation left to trim.

5 / 5

Actionability

Guidance is concrete and executable: named workflow actions ('promote-stable'), named files ('ts.release.yml', 'references/release-workflow.md'), a read-only preflight, and a specified report payload (tag, source, workflow URL, asset state, install-test result). The referenced playbook supplies copy-paste 'gh workflow run' / 'gh release view' commands covering all four request paths, satisfying the 5 anchor; per the scoring notes, absence of inline code in an orchestration-layer skill is not penalized when the routing is this specific.

5 / 5

Workflow Clarity

The Execution section is a clear 5-step sequence (classify → preflight → dispatch → verify → report) with explicit validation checkpoints ('Follow the release through asset verification and installation tests. Do not stop after the dispatch succeeds') and a confirmation checkpoint before the production write. Recovery is a first-class classification routed to a dedicated Failure Recovery playbook section, matching the 5 anchor's feedback loops and checklist (the Release Contract) rather than the 4 anchor, which requires only 'most' checkpoints.

5 / 5

Progressive Disclosure

A 29-line overview with well-organized sections that delegates execution detail via a single clearly signaled, one-level-deep reference ('Read references/release-workflow.md before selecting a candidate or dispatching a workflow'), which exists and itself contains no nested bundle references. This matches the 5 anchor: appropriate split, easy navigation, no buried or chained references.

5 / 5

Total

20

/

20

Passed

Description

92%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: comprehensive and concrete about capabilities, with explicit use-when triggers covering the full request lifecycle (build, publish, promote, choose, monitor, diagnose) and explicit exclusions that sharply bound its scope. The only minor gap is a few missing synonymous trigger phrasings.

DimensionReasoningScore

Specificity

The description enumerates multiple concrete actions — 'automatic beta builds, promote-stable dispatches, beta-tag selection, asset and installation verification, and failed release recovery' — comprehensively covering the release lifecycle. This matches the score-5 anchor (multiple specific concrete actions, comprehensive coverage) rather than 4, since no meaningful action in the domain is left out.

5 / 5

Completeness

It explicitly answers both 'what' ('Release and recover first-party Composio CLI binaries through Build CLI Binaries, including...') and 'when' ('Use when a contributor asks to build a CLI beta, publish or promote a stable CLI version...') with concrete trigger phrases, plus a negative-scope clause. This matches the 5 anchor exactly; the 4 anchor's caveat about a less-explicit 'when' does not apply.

5 / 5

Trigger Term Quality

Triggers like 'build a CLI beta', 'publish or promote a stable CLI version', 'choose a release candidate', 'monitor a CLI release', and 'diagnose a failed CLI release' are natural phrases users would say, giving good keyword coverage across the lifecycle. It falls short of the 5 anchor because a few natural variations (e.g., 'ship a CLI release', 'cut a version', 'roll back a release') are absent.

4 / 5

Distinctiveness Conflict Risk

The niche is sharply defined ('first-party Composio CLI binaries through Build CLI Binaries') and the explicit exclusion 'Do not use for TypeScript SDK Changesets releases or CLI source implementation' actively disambiguates the two adjacent skills most likely to collide. Clear niche with distinct triggers and minimal conflict risk — the 5 anchor.

5 / 5

Total

19

/

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

ComposioHQ/composio

Path

.agents/skills/cli-release/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.