CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

pr-iterate

One closed-loop iteration on an open PR — read CI checks + bot and human review comments, triage against this repo's decision records, apply valid suggestions, reply with reasoning on rejected ones, push fixes as Conventional Commits, and report status. Invoke as `/pr-iterate <PR#>`. Compose with `/loop /pr-iterate <PR#>` for continuous monitoring until green.

Quality

91%

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

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.

Excellent operational content: copy-paste-ready commands, explicit validation and stop conditions, and tight tables make it immediately executable. The only refinement opportunities are trimming a few rationale paragraphs and potentially offloading the triage matrix or output template to a reference file.

DimensionReasoningScore

Conciseness

The body is dense and operational — tables, exact commands, and rules with almost no explanation of concepts Claude already knows — but a few justificatory passages could be trimmed (e.g., the merge-method/release-notes rationale in hard rule 6 and the reviewer-lenses paragraph in step 2), fitting the 'efficient with minor over-explanation' anchor rather than 'every token earns its place'.

4 / 5

Actionability

Fully executable throughout: prerequisite checks with abort codes, `gh pr view --json` with exact field lists, `gh api` endpoints for inline review-thread comments, `gh run view --log-failed`, a heredoc commit-message template, per-endpoint reply commands, a GraphQL resolve mutation, and a bounded wait loop — copy-paste ready and covering all common cases (failing checks, bot threads, human threads).

5 / 5

Workflow Clarity

A six-step numbered procedure with an explicit validation preamble (clean worktree, correct branch, up-to-date with origin, each with abort behavior), feedback loops (pre-push hooks treated as signal to fix the cause, not bypass; 5-iteration stall cap), enumerated stop conditions, and a defined escalation path plus output format — the destructive-operation cap does not apply since validation is thoroughly present.

5 / 5

Progressive Disclosure

No bundle files exist; the single ~227-line file is well-sectioned with clear headers, and cross-references (to /review-pr, /implement, repo records) are clearly signaled and one level deep. Structure is good, but nothing is progressively offloaded — the triage matrix and output template are long inline candidates for a reference file, so it sits at 'good structure, minor organization gaps' rather than the ideal split.

4 / 5

Total

18

/

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: concrete, comprehensive, and explicitly invocable in both manual and loop modes with a distinct niche. The only gap is modest synonym coverage of natural trigger phrasings.

DimensionReasoningScore

Specificity

The description lists six concrete actions covering the full iteration lifecycle — "read CI checks + bot and human review comments, triage against this repo's decision records, apply valid suggestions, reply with reasoning on rejected ones, push fixes as Conventional Commits, and report status" — matching the comprehensive-coverage anchor, exceeding the 'minor gaps' level 4.

5 / 5

Completeness

Both what and when are answered explicitly with concrete trigger phrases: the six actions state what, and "Invoke as `/pr-iterate <PR#>`. Compose with `/loop /pr-iterate <PR#>` for continuous monitoring until green" gives explicit invocation guidance for both modes — equivalent to a 'Use when' clause, so the level-3 cap does not apply.

5 / 5

Trigger Term Quality

Good natural keyword coverage for the domain ("PR", "CI checks", "review comments", "bot and human review comments", "Conventional Commits", "iteration"), but a few natural phrasings users would say are missing (e.g., "pull request" spelled out, "failing checks", "address review feedback", "get checks green"), keeping it below the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

It carves a clear niche — one closed-loop iteration on an open PR toward green — with a unique slash-command trigger, and even scopes itself against neighbors (never merges; applying/replying rather than opening or reviewing), so overlap with related skills is minimal.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 1 possibly missing (scripts/check.sh)

Warning

Total

15

/

16

Passed

Repository

agranado2k/google-books-clojure

Path

.claude/skills/pr-iterate/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.