pr-gardening

Discover recently referenced Paperclip pull requests, mechanically verify their current-head readiness, drive non-draft PRs back to green through their originating issues, and publish a merge-confidence report without merging.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/pr-gardening/SKILL.md

Quality

Content

85%

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 and well-structured with explicit validation loops and real, correctly-referenced bundle scripts, making it a strong procedural skill. The only weakness is mild verbosity from guardrail restatements that recur across stages.

Suggestions

Consolidate the repeated read-only / never-merge guardrails into the single Hard Guardrails section and reference it from later stages rather than restating each rule per stage.

Consider moving the long Stage D 'do not archive' enumeration and the suggested comment bodies into a reference file to slim the inline SKILL.md body.

Trim duplicated phrases such as "GitHub access remains read-only" which appears in multiple stages.

Dimension	Reasoning	Score
Conciseness	The body assumes Claude's competence with no concept padding and earns most of its tokens, but it restates the read-only / never-merge guardrails across several stages (e.g. "GitHub access remains read-only", "Never merge") that could be consolidated, matching "mostly efficient but could be tightened" rather than the every-token-earns-its-place anchor at 3.	2 / 3
Actionability	Every stage gives fully executable `node .../scripts/*.mjs` commands with exact arguments, concrete Paperclip POST endpoints with required headers, exact HTML marker strings, and a copy-paste comment body, matching the fully-executable anchor at 3.	3 / 3
Workflow Clarity	Stages A–F are clearly sequenced with explicit validation checkpoints — "Always rerun this stage after any wake", rerun Stage B before Stage D, GitHub-confirmed merged-at-same-head requirement, and a `node --test` verification step — matching the explicit-feedback-loop anchor at 3.	3 / 3
Progressive Disclosure	The body is an organized stage-by-stage overview that references real one-level-deep bundle scripts (find-candidates.mjs, check-readiness.mjs, render-report.mjs all exist in ./scripts/), with detail deferred to those scripts and clearly signaled by stage headers, matching the well-signaled one-level-deep anchor at 3.	3 / 3
	Total	11 / 12 Passed

Description

67%

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 and distinctive, naming several concrete actions and a clear niche, but it never states when Claude should invoke the skill. Adding an explicit "Use when..." clause with natural user phrasing would lift completeness and trigger-term quality.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user wants to triage or revive failing/open Paperclip-referenced pull requests, or asks to 'garden PRs' or 'get PRs green'."

Add natural-language synonyms users would actually say ("failing CI", "stale PR", "fix the build") alongside the current jargon to broaden trigger coverage.

Keep the concrete action list but consider "non-draft" phrasing as "open (non-draft)" so the trigger reads more naturally.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "Discover recently referenced Paperclip pull requests", "mechanically verify their current-head readiness", "drive non-draft PRs back to green", and "publish a merge-confidence report" — matching the multi-action anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	It clearly answers what the skill does but lacks an explicit "Use when..." trigger, so "when" is only implied; the judging guidelines cap completeness at 2 for a missing explicit trigger clause, ruling out 3.	2 / 3
Trigger Term Quality	It contains relevant terms ("pull requests", "readiness", "merge-confidence report") but leans on jargon ("current-head readiness", "drive back to green") and omits common user phrasings, so it matches "some relevant keywords but missing common variations" rather than full coverage at 3.	2 / 3
Distinctiveness Conflict Risk	"Paperclip pull requests" and "merge-confidence report without merging" carve a clear niche unlikely to trigger for unrelated skills, matching the distinct-trigger anchor at 3 rather than the overlapping-skill anchor at 2.	3 / 3
	Total	10 / 12 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: 14f20be

Reviewed: 4 days 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.