pr-gardening

Discover the pull requests this Paperclip instance opened (never community contributions), report what each is for and how confident we are that it is merge-ready, and automatically drive the non-ready ones back to green with /prepare-paperclip-pr — without ever merging.

Quality

80%

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 ./.agents/skills/pr-gardening/SKILL.md

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.

The content is highly actionable, well-sequenced with validation feedback loops, and uses progressive disclosure effectively by deferring detail to real, path-referenced scripts. The only mild weakness is repeated restatement of the merge/approve/close guardrails that could be consolidated.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence with no concept padding, but the same guardrail (never merge/approve/close) is restated several times across sections and a few of those repetitions could be trimmed.	4 / 5
Actionability	It provides fully executable, copy-paste-ready commands (e.g. 'node .agents/skills/pr-gardening/scripts/find-candidates.mjs --days 14 --dry-run'), concrete API endpoints with headers, exact marker-comment strings, and idempotency keys covering the common cases.	5 / 5
Workflow Clarity	Stages A through F are clearly sequenced with explicit validation checkpoints and feedback loops (rerun Stage B after any wake or claim of a fix, require GitHub state:merged at the same head before archiving, stop after three rounds), which is exactly what batch/destructive operations require.	5 / 5
Progressive Disclosure	The body is a clear overview with well-signaled, one-level-deep references to real bundle scripts (find-candidates.mjs, check-readiness.mjs, render-report.mjs, pr-gardening.test.mjs, lib.mjs) invoked by exact path, with bulk detail deferred to those scripts rather than inlined.	5 / 5
	Total	19 / 20 Passed

Description

67%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 is specific, concrete, and highly distinct, but it omits an explicit 'Use when...' trigger clause, leaving the 'when to invoke' dimension only weakly implied. Adding a trigger phrase would raise completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when...' clause stating the natural invocation triggers (e.g. 'Use when the user asks to garden, triage, or check the readiness of this instance's open pull requests').

Include common synonyms the user would naturally say, such as 'PRs', 'merge readiness', or 'pull request status', to broaden trigger-term coverage.

Lead with the 'what' in a tighter single sentence and reserve the parenthetical scope/merge constraints for a second sentence to keep the description scannable.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (discover PRs, report purpose and merge-readiness confidence, drive non-ready PRs to green via /prepare-paperclip-pr) plus an explicit hard constraint ('without ever merging'), giving comprehensive coverage of the domain.	5 / 5
Completeness	It clearly answers 'what' the skill does but provides no explicit 'when' / 'Use when...' trigger guidance, which per the rubric guideline caps completeness at 3.	3 / 5
Trigger Term Quality	It has some relevant natural keywords ('pull requests', 'merge-ready', 'drive back to green') but is missing common variations and synonyms (e.g. 'PRs', 'PR gardening', 'merge readiness') and leans on Paperclip-specific jargon.	3 / 5
Distinctiveness Conflict Risk	The description carves out a clear niche (PRs this Paperclip instance opened, gardening to merge-ready with /prepare-paperclip-pr) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	16 / 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: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: paperclipai/paperclip
Path: .agents/skills/pr-gardening/SKILL.md
Commit: af3023f

Reviewed: ~20 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.