warp-release-audit

Use when generating a Warp pre-release or release-candidate audit report from Towncrier fragments and release history.

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/warp-release-audit/SKILL.md

Quality

Content

73%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 content is an exceptionally well-structured, actionable workflow with strong validation checkpoints and a clean one-level reference map. Its main weakness is conciseness: the SKILL.md body carries a large amount of inline policy and formatting detail that makes it long for an overview file.

Suggestions

Move inline formatting and output-style hard constraints (no em dashes, hyperlink rules, table column specs) into render-rules.md and keep only a one-line pointer plus the most critical rule, reducing body length.

Consolidate the dense 4a-4h sub-steps into the classification-rules reference where possible, surfacing only the decision flow and validation steps in the body.

Tighten prose-only guidance passages (e.g. the highlight-selection rationale in 6a) into shorter checklists so the overview stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is highly specific and free of generic concept padding, but at ~490 lines it is dense with inline rules, fallback branches, and formatting constraints that could be offloaded to reference files; it is mostly efficient yet could be tightened and is noticeably long for a SKILL.md overview.	3 / 5
Actionability	It provides concrete, executable bash and Python snippets (git tag enumeration, worktree setup, uvx towncrier draft, the diff_public_api.py invocation) with minor gaps; some guidance remains procedural prose rather than copy-paste commands, and a few placeholders require user substitution.	4 / 5
Workflow Clarity	The six phases are clearly sequenced with explicit validation checkpoints and feedback loops (wait for user confirmation in Phase 1, verify signatures at base and HEAD in 4g with build/test/compare/restore, reconcile mode mismatches, always clean up the worktree even on failure), which matches the top anchor for destructive/batch operations.	5 / 5
Progressive Disclosure	References are well-signaled and one level deep (destination-rules, classification-rules, language-review-examples, report-template, render-rules, two scripts), all confirmed to exist, and a clear map of which reference loads in which phase is given up front; it is not a 5 because substantial rule and formatting detail is still inlined in the body rather than fully delegated.	4 / 5
	Total	16 / 20 Passed

Description

71%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 has a clear, explicit Use-when trigger and answers both what and when, giving it strong completeness. Specificity and trigger-term breadth are solid but not comprehensive, listing the core action without enumerating the multiple distinct operations the skill performs.

Suggestions

Enumerate a few more concrete actions in the description (e.g. detecting breaking changes, diffing the public API surface, deprecation-window lookups) to lift specificity above a single named action.

Add natural synonyms users might say, such as 'release notes', 'changelog review', or 'pre-release check', to broaden trigger-term coverage.

Dimension	Reasoning	Score
Specificity	It names the domain (Warp release audit) and one concrete action (generating a markdown audit report) plus the inputs it draws on, but does not enumerate multiple specific actions like keep/defer decisions, breaking-change detection, or API-surface diffing that the skill actually performs.	3 / 5
Completeness	It explicitly answers both 'what' (generates a markdown audit of the upcoming Warp release for keep/defer decisions) and 'when' (Use when generating a Warp pre-release or release-candidate audit report from Towncrier fragments and release history) with a concrete trigger clause.	5 / 5
Trigger Term Quality	It includes the natural phrase 'audit report' and 'release-candidate', but omits common variations a user would say (release notes, changelog review, pre-release check) and any file-extension or tool-style triggers; coverage is relevant but partial.	3 / 5
Distinctiveness Conflict Risk	The niche is clear and narrowly scoped to Warp release auditing from Towncrier fragments, so conflict risk with other skills is low; it is not a maximal 5 only because 'audit report' and 'release' are terms that could weakly overlap with generic review or release-tooling skills.	4 / 5
	Total	15 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 4 suspicious	Warning

	Total	15 / 16 Passed

Repository: NVIDIA/warp
Path: .claude/skills/warp-release-audit/SKILL.md
Commit: 238de60

Reviewed: 5 days ago

Table of Contents

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.