CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

warp-closing-issue

Use when the user provides Warp commit SHA(s) and GitHub issue number(s) to assess, draft issue comments, post progress updates, or recommend whether issue threads should stay open or close.

Quality

94%

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

The canonical home for this skill is warp-closing-issue in NVIDIA/warp

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 instruction-only skill: the workflow is unambiguous, every public-facing output has a copy-paste template, and risky GitHub writes are protected by layered validation gates and confirmation steps. The only cost is deliberate restatement of critical rules across three sections, which trims token efficiency slightly.

DimensionReasoningScore

Conciseness

The body is dense and prescriptive with no padding and no explanations of concepts Claude already knows; every line is skill-specific policy. However, key rules (full-SHA usage, excluding local execution details, confirmation before writes) are restated across "Core rules", the workflow steps, and "Red flags", which is trimmable redundancy — anchor 4 rather than the fully lean anchor 5.

4 / 5

Actionability

Guidance is fully executable: copy-paste-ready markdown draft templates, concrete classification taxonomies (Exact/Partial/None found/Inconclusive; addressed/progress; close/comment-only), specific API fields (user.login, author.login, committer.login), and concrete commands (uv run, WARP_CACHE_PATH, uv run tools/pre-commit-hooks/sync_skills.py --from codex). This matches anchor 5.

5 / 5

Workflow Clarity

The eight-step workflow is clearly sequenced with explicit validation checkpoints: a scope gate with defined stop conditions, reproduction results (passes/fails in scope/inconclusive/not run) that gate closure, mandatory user confirmation before any write, and post-write read-back verification with "Stop on a write failure". This matches anchor 5's feedback-loop and error-recovery pattern.

5 / 5

Progressive Disclosure

Three one-level-deep reference files (changelog-evidence.md, public-api-comments.md, commands.md) all exist, contain real content, and are conditionally loaded with explicit triggers (changelog content, public API relevance, mandatory before GitHub writes). Navigation is clear and nothing is nested, matching anchor 5.

5 / 5

Total

19

/

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: it explicitly pairs a concrete when-clause with a specific multi-action what in a well-delineated niche. The only minor weakness is missing a few natural trigger variations, which keeps trigger-term coverage at good rather than comprehensive.

DimensionReasoningScore

Specificity

The description lists four concrete actions in a specific domain ("assess, draft issue comments, post progress updates, or recommend whether issue threads should stay open or close"), covering the workflow comprehensively. It matches the anchor-5 example of multiple specific concrete actions rather than the anchor-4 case, which requires minor coverage gaps.

5 / 5

Completeness

Both what and when are explicit: "Use when the user provides Warp commit SHA(s) and GitHub issue number(s)" is a concrete trigger clause, and the action list states exactly what the skill does. This matches anchor 5; it exceeds anchor 4 because the when-clause is specific rather than generic.

5 / 5

Trigger Term Quality

Natural trigger phrases are present ("Warp commit SHA(s)", "GitHub issue number(s)", "issue comments", "progress updates", "stay open or close") that a user would plausibly say. A few common variations (e.g., "close the issue", "triage", "link commits to issues") are missing, matching anchor 4 rather than the synonym-level comprehensiveness of anchor 5.

4 / 5

Distinctiveness Conflict Risk

The "Warp commit SHA(s)" trigger carves out a clear niche distinct from generic GitHub issue-management or commit-message skills, with minimal conflict risk. This matches anchor 5 (clear niche with distinct triggers).

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

NVIDIA/warp

Path

.codex/skills/warp-closing-issue/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.