CtrlK
BlogDocsLog inGet started
Tessl Logo

prp-issue

Autonomously owns one workstream from an issue, PRD, document, existing plan, or free-form request through planning, implementation, pull request, independent review, corrections, and green CI. Always use when the user asks to implement or ship work end to end, take an issue or idea to a reviewed PR, run plan to PR, invokes $prp-issue, or when prp-orchestrate needs an end-to-end delivery engine.

73

Quality

92%

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

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.

An exceptionally well-constructed orchestration skill: every phase has explicit entry gates, exit criteria, and failure-recovery loops, and the reviewer-launch prompt and CI watcher commands are copy-paste concrete. The single deduction is repetition of the tiny-work rule, which is stated in five places and could be consolidated.

DimensionReasoningScore

Conciseness

The body is dense, purely directive prose with zero padding or concept explanation (e.g., "Never point a reviewer at your own working tree"), but the tiny-work rule is restated across the Contract, §1, §2, §3, and §6, which could be trimmed. This fits the level-4 anchor (efficient with minor trimmable instances) rather than level-5 (every token earns its place) or level-3 (noticeably unnecessary explanation).

4 / 5

Actionability

Guidance is fully executable for an instruction-only skill: a copy-paste reviewer-launch prompt in §3, the exact watcher command `timeout 1800 gh pr checks <n> --required --watch --fail-fast`, explicit gates ("Do not start review without `VALIDATION: GREEN`"), and named disposition states (DECLINED, TRACKED FOLLOW-UP, NOT A FINDING). Specific templates cover the common cases, matching the level-5 anchor.

5 / 5

Workflow Clarity

Six numbered phases (§1–§6) are clearly sequenced with explicit validation checkpoints at every boundary ("Do not start review without VALIDATION: GREEN", "Only after review and CI are green, return ...") and explicit feedback loops: correction batches re-enter `$prp-implement` in review-correction mode, blocking fixes trigger `$prp-review --verify-corrections`, and CI failures route through CI-correction mode then re-verification. This matches the level-5 anchor.

5 / 5

Progressive Disclosure

The skill is a single self-contained ~75-line file with no bundle directories (references/, scripts/, assets/ do not exist), no nested references, and numbered sections that make navigation trivial. Nothing here warrants splitting into separate files, so the well-organized single-file structure earns the top score rather than the level-4 anchor with organization gaps.

5 / 5

Total

19

/

20

Passed

Description

88%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: it states both what the skill does and exactly when to use it, with concrete natural-language triggers and comprehensive lifecycle coverage. Its only weakness is moderate keyword breadth — a few common synonyms for end-to-end delivery are missing, and the broad 'implement' phrasing slightly raises conflict risk with sibling skills.

DimensionReasoningScore

Specificity

The description enumerates concrete lifecycle actions ("through planning, implementation, pull request, independent review, corrections, and green CI") and concrete input types ("issue, PRD, document, existing plan, or free-form request"), all in third-person voice ("Autonomously owns"). Coverage of the delivery lifecycle is comprehensive, matching the level-5 anchor rather than the level-4 anchor with minor gaps.

5 / 5

Completeness

Both halves are explicit: a concrete what ("owns one workstream ... through planning, implementation, pull request, independent review, corrections, and green CI") and an explicit "Always use when" clause with multiple concrete trigger phrases. This matches the level-5 anchor; the level-4 anchor's weaker or less specific when-clause does not apply.

5 / 5

Trigger Term Quality

It includes natural user phrasings like "implement or ship work end to end", "take an issue or idea to a reviewed PR", and "run plan to PR", plus self-referential triggers ("invokes $prp-issue", "prp-orchestrate"). It falls short of the level-5 anchor because common synonyms such as "deliver", "finish this ticket", or "get this PR-ready" are absent.

4 / 5

Distinctiveness Conflict Risk

Qualifiers like "end to end", "reviewed PR", "$prp-issue", and "prp-orchestrate needs an end-to-end delivery engine" carve a clear niche against sibling prp-* skills, but the broad opening "when the user asks to implement ... work" carries minor overlap risk with a plain implementation skill, fitting the level-4 rather than level-5 anchor.

4 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Wirasm/prp
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.