prp-worklist

Render the open work of a repository as something worth looking at, so the maintainer can see what to take next. Deliberate invocation only — $prp-worklist.

Quality

50%

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/prp-worklist/SKILL.md

Quality

Content

55%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 body is admirably lean and well-structured, and it candidly frames itself as deliberately underspecified — but that spec-looseness costs actionability and workflow clarity, since it gives almost no executable steps and no validation before writing to the persistent store. Progressive disclosure is good for a short, self-contained skill.

Suggestions

Add a minimal concrete sequence for the core loop (e.g. `gh issue list` / `gh pr list` flags to start from, and the exact path/link format to write under ~/.prp/<key>/) so the guidance is executable rather than advisory.

Insert a validation checkpoint before offering the worklist (e.g. confirm the file was written and the link opens) to lift workflow clarity and cover the batch/persistent-write context.

Give one concrete example of the output shape (a short sample worklist grouping) so 'decide how to show it' has a floor rather than being entirely open-ended.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it states the job, the maintainer's considerations, and the shape without padding or explaining concepts Claude already knows; every line earns its place.	5 / 5
Actionability	It gives one concrete pointer ('Read the tracker with `gh`') but otherwise offers only high-level hints ('weigh them, drop the ones that do not apply', 'offer it rather than pasting it') with no executable steps, matching 'minimal concrete guidance; high-level hints but missing the specific steps'.	2 / 5
Workflow Clarity	A rough sequence exists (read tracker with gh -> decide what to show -> write to ~/.prp/<key>/ -> print a link -> report choices) but steps are loosely defined with no validation checkpoints; the destructive/batch cap also applies since writing to the store lacks any verify step, keeping it below 3.	2 / 5
Progressive Disclosure	Structure is good with well-separated sections (The job, What this maintainer cares about, Shape, Report your choices) and one clearly signaled external pointer (the ~/.prp/<key>/ store and optional helm-canvas skill); it does not reach 5 because there are no actual reference files to navigate to and the 'considerations' block is somewhat dense inline.	4 / 5
	Total	13 / 20 Passed

Description

46%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 states the skill's purpose clearly in third person and carves out a distinct maintainer-facing niche, but it lacks an explicit 'when to use it' trigger clause and natural user-spoken keywords, leaning on the technical '$prp-worklist' invocation instead. Completeness is capped at 3 by the missing trigger guidance.

Suggestions

Add an explicit 'Use when the maintainer asks what to take next, what to work on, or wants to triage open issues and PRs' clause to satisfy the 'when' half of completeness.

Surface natural user phrases ('what should I work on next', 'triage the backlog', 'worklist') so the trigger matches how users actually ask rather than only the '$prp-worklist' token.

Name a second concrete action (e.g. 'group near-duplicates and flag stale issues') to lift specificity above a single rendered view.

Dimension	Reasoning	Score
Specificity	It names the domain (rendering a repo's open issues/PRs as 'what to take next') but lists only one concrete action — rendering/offering a worklist — rather than multiple specific operations, matching the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	The 'what' is clearly stated ('Render the open work of a repository... so the maintainer can see what to take next'), but the 'when' is only weakly implied by 'Deliberate invocation only' — there is no explicit 'Use when...' trigger phrase, which caps completeness at 3 per the guidelines.	3 / 5
Trigger Term Quality	The only natural term is 'open issues and PRs'; there is no equivalent of common user phrasings like 'what should I work on', 'worklist', or 'triage', and it leans on the technical '$prp-worklist' invocation rather than user-spoken keywords.	2 / 5
Distinctiveness Conflict Risk	The niche is fairly distinct — a maintainer-facing worklist view of a repo's open issues/PRs — with only minor overlap risk against generic issue-triage skills; it does not reach 5 because the trigger guidance is thin enough that it could be invoked loosely.	4 / 5
	Total	12 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Wirasm/prp
Path: .agents/skills/prp-worklist/SKILL.md
Commit: d62c3ae

Reviewed: 5 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.