Name: iterate-pr
Rating: 68.8 (1 reviews)
Author: administrakt0r

iterate-pr

Iterate on a PR until CI passes. Use when you need to fix CI failures, address review feedback, or continuously push fixes until all checks are green. Automates the feedback-fix-push-wait cycle.

Quality

84%

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

The canonical home for this skill is iterate-pr in administrakt0r/AI-Agents-Safe-Coding-Skills

Quality

Content

85%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 highly actionable, well-sequenced workflow with strong validation and feedback loops. Its main weakness is progressive disclosure: the bundled scripts it depends on are not actually present in the bundle, leaving broken references.

Suggestions

Ship the referenced scripts (scripts/fetch_pr_checks.py and scripts/fetch_pr_feedback.py) in the bundle, or replace the references with inline gh-based fallback commands so the skill is self-contained.

Remove or replace the generic 'When to Use' filler paragraph with concrete, specific trigger conditions to tighten conciseness.

Consider extracting the LOGAF categorization detail and JSON contracts into a short reference file, keeping SKILL.md as a lean overview with clearly signaled one-level-deep links.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and JSON contracts that earn their place, but contains minor padding such as the generic 'When to Use' boilerplate ('Use this skill when tackling tasks related to its primary domain or functionality') and a few directive sentences restating what Claude already knows.	4 / 5
Actionability	Provides fully executable, copy-paste-ready guidance throughout — 'uv run ${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py', 'gh pr view --json number,url,headRefName', 'git add/commit/push', and the named 'addPullRequestReviewThreadReply' GraphQL mutation — with JSON output contracts covering common cases.	5 / 5
Workflow Clarity	An 8-step workflow with explicit sequencing, validation checkpoints ('If local verification fails, fix before proceeding — do not push known-broken code', reply-dedup check before posting), and feedback loops (step 7 polling loop, step 8 repeat cycle) plus explicit exit conditions.	5 / 5
Progressive Disclosure	The SKILL.md is well-sectioned but everything lives in one file with no actual reference files split out, and the body references scripts via '${CLAUDE_SKILL_ROOT}/scripts/fetch_pr_checks.py' and 'fetch_pr_feedback.py' that do not exist in the bundle (no scripts/ directory is present), so the signaled references do not resolve.	3 / 5
	Total	17 / 20 Passed

Description

83%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 clearly states both capability and trigger conditions with natural language. It is specific and actionable, with only minor gaps in action enumeration and trigger synonyms.

Dimension	Reasoning	Score
Specificity	Names the PR/CI domain and several concrete actions — 'fix CI failures', 'address review feedback', 'continuously push fixes' — but does not enumerate the full range of operations (e.g., replying to threads, polling), so minor coverage gaps keep it below 5.	4 / 5
Completeness	Explicitly answers both what ('Iterate on a PR until CI passes... Automates the feedback-fix-push-wait cycle') and when ('Use when you need to fix CI failures, address review feedback, or continuously push fixes') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural phrases users would say ('fix CI failures', 'address review feedback', 'all checks are green') with good coverage, but lacks common synonyms/variants like 'red CI', 'failing builds', or 'make CI green'.	4 / 5
Distinctiveness Conflict Risk	The 'iterate until CI passes' niche is fairly distinct with specific triggers, though it has minor overlap risk with general PR-review or commit-message skills.	4 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 2 missing	Warning

	Total	14 / 16 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: plugins/AI-Agents-Safe-Coding-Skills-claude/skills/iterate-pr/SKILL.md
Commit: 731a928

Reviewed: 19 hours 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.