CtrlK
BlogDocsLog inGet started
Tessl Logo

warp-changelog-audit

Use when auditing and recovering Warp changelog fragments, finalizing a release changelog, or synchronizing a tagged release back to main.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is warp-changelog-audit in NVIDIA/warp

SKILL.md
Quality
Evals
Security

Quality

Content

88%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 dense, highly executable release-changelog process skill with strong command specificity and rigorous validation/confirmation checkpoints throughout. Its only real weakness is length-driven token cost that a tighter Failure-modes/Final-report pass could reduce.

Suggestions

Tighten the Failure modes and Final report sections into terse checklists to trim token cost without losing the validation signal.

Consider moving the Parsing rules regex block into a reference file so the SKILL.md body stays a navigable overview.

Collapse near-duplicate confirmation instructions across phases into a single stated rule referenced by each phase.

DimensionReasoningScore

Conciseness

Lean and command-dense with no padding or basic-concept explanations, but the ~340-line body has a few sections (Failure modes, Final report) that could be tightened without losing signal.

4 / 5

Actionability

Copy-paste-ready pinned commands ('uvx --from towncrier==25.8.0 towncrier build --draft', exact git log/ls-tree invocations) and concrete regex parsing rules cover the common cases fully.

5 / 5

Workflow Clarity

Six clearly sequenced phases with explicit validation checkpoints and feedback loops ('Wait for explicit confirmation', 're-run the draft', 'stop if they differ unexpectedly') appropriate for destructive/batch release operations.

5 / 5

Progressive Disclosure

Process lives in SKILL.md while conventions are split into clearly signaled, one-level-deep real reference files (language-conventions.md, sorting-rubric.md); minor organization gaps remain in the long inline process body.

4 / 5

Total

18

/

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, third-person description that explicitly states both capabilities and trigger conditions for a well-scoped niche. Minor synonym coverage and edge-action gaps keep trigger and specificity just below perfect.

DimensionReasoningScore

Specificity

Lists several concrete actions ('auditing and recovering Warp changelog fragments', 'finalizing a release changelog', 'synchronizing a tagged release back to main') with only minor coverage gaps, stopping short of the fully comprehensive 5-anchor example.

4 / 5

Completeness

Clearly answers both what (audit/recover/finalize/sync changelog fragments) and when via an explicit 'Use when...' clause with three concrete trigger phrases.

5 / 5

Trigger Term Quality

Good natural-term coverage ('auditing', 'changelog fragments', 'release changelog', 'finalizing a release', 'synchronizing a tagged release') a user would say, though synonyms like 'release notes' are absent.

4 / 5

Distinctiveness Conflict Risk

A narrow Warp-specific changelog release workflow with distinct triggers and minimal realistic overlap with other skills.

5 / 5

Total

18

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
NVIDIA/warp
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.