Tessl • The management layer for AI agent skills

Blog Docs Log inGet started

SkillPublic

release

Release a stable verifiers version from main to PyPI and GitHub.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/release/SKILL.md

Quality

Content

86%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.

The body is an exemplary lean, command-driven runbook: a clear default-version policy, five well-sequenced steps with concrete executable commands, pre-tag safety checks, and a final verification checklist. The only meaningful gaps are the unspecified release-note format and missing recovery guidance for a failed publish run or failed verification. No bundle files exist, so structure is appropriately contained in SKILL.md itself.

Dimension	Reasoning	Score
Conciseness	The body is command-first and lean throughout ("By default, bump to the next minor `vX.Y.Z` version unless the user specifies a different target version", one-line confirmations per step) with no explanations of concepts Claude already knows; every token earns its place. The `vX.Y.Z` occurrences are placeholders, not time-sensitive version pins, so no penalty applies.	5 / 5
Actionability	Guidance is mostly copy-paste executable (`git tag "$VERSION"`, `gh workflow run publish.yml --repo PrimeIntellect-ai/verifiers --ref main -f tag="$VERSION"`, `gh run watch <run-id> --exit-status`, `gh release edit ... --notes-file`). Minor gaps keep it below 5: "the same release-note format" delegates the format to prior releases without a pointer, and `<release-notes.md>` implies writing a file first without saying so.	4 / 5
Workflow Clarity	A clear 5-step sequence with explicit checkpoints (clean worktree, version not already published, remote tag points to the main commit, watch with --exit-status, and a final verify checklist for PyPI wheel+sdist, public release assets, and notes format) plus one conditional recovery loop (dev-version dependencies → normal PR → re-pull). Not 5 because there is no error-recovery guidance if the publish workflow fails or the final verification fails.	4 / 5
Progressive Disclosure	This is a single-purpose, self-contained skill with no bundle files and nothing inlined that belongs in a separate file; the numbered sections are well organized and easy to navigate. Per the simple-skill guideline, well-organized sections with no need for external references score 5.	5 / 5
	Total	18 / 20 Passed

Description

53%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.

The description gives a clear, concrete statement of what the skill does and where, and is well scoped to a specific package. Its main weakness is the complete absence of when-to-use trigger guidance, which both caps completeness and leaves trigger-term coverage thin. Adding a "Use when the user asks to release, publish, or cut a version of verifiers" clause would lift the two lowest dimensions.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to release, publish, or tag a new verifiers version to PyPI or GitHub."

Include natural synonym keywords such as "publish" and "tag" so the description matches how users actually phrase the request.

Optionally enumerate the concrete release actions (bump version, tag, dispatch publish workflow, update release notes, verify) to raise specificity.

Dimension	Reasoning	Score
Specificity	"Release a stable verifiers version from main to PyPI and GitHub" names the domain and one concrete action with concrete sources and destinations, but does not enumerate the several distinct release actions (tagging, workflow dispatch, release notes), matching the 1-2-concrete-actions anchor. It is more concrete than a bare domain statement (2) but not the several-specific-actions coverage of 4.	3 / 5
Completeness	The "what" is clear (release a stable version from main to PyPI and GitHub), but there is no "Use when..." clause or equivalent trigger guidance, which caps completeness at 3 per the judging guidelines. Not 4 because the "when" is entirely absent rather than merely under-specified.	3 / 5
Trigger Term Quality	Relevant natural terms are present ("Release", "version", "PyPI", "GitHub", "verifiers"), but common variations users would say such as "publish" or "cut a release" are missing, matching the some-keywords-missing-synonyms anchor. Not 4 because the natural-term coverage is thin for a one-sentence description.	3 / 5
Distinctiveness Conflict Risk	Naming the specific package ("verifiers") and destinations ("PyPI", "GitHub", "main") makes it mostly distinct with only minor overlap risk against a hypothetical generic release/publishing skill. Not 5 because the anchor expects distinct explicit triggers, and "verifiers" is also a common ML term that could pull unrelated queries.	4 / 5
	Total	13 / 20 Passed

Validation

100%

Warnings & errors only

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: PrimeIntellect-ai/verifiers
Path: skills/release/SKILL.md
Revision: eaab317

Reviewed: 18 days ago

Discovery Implementation Validation

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.

release

Table of Contents

Is this your skill?