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.

72

Quality

90%

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

88%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 excellent orchestration skill body: it sequences a complex multi-agent lifecycle with explicit gates and feedback loops, provides verbatim prompts and commands for the critical handoffs, and assumes Claude's competence throughout. Its only imperfections are minor redundancy around the tiny-work rules and gate restatements, and a couple of dense passages that could be externalized to reference files.

DimensionReasoningScore

Conciseness

The body is dense and telegraphic ('Compose /prp-plan, /prp-implement, and /prp-review; do not reproduce their craft') with no explanation of concepts Claude already knows. However, the tiny-work rules are restated across §1, §2, and §6 and gate conditions like 'VALIDATION: GREEN' recur, leaving minor tightening opportunities that keep it below the every-token-earns-its-place anchor 5. It is well above the 'several unnecessary explanations' level 3 anchor.

4 / 5

Actionability

Guidance is copy-paste ready: a verbatim fresh-agent reviewer prompt template, an exact watcher command ('timeout 1800 gh pr checks <n> --required --watch --fail-fast'), an explicit disposition taxonomy (TRACKED FOLLOW-UP, DECLINED, NOT A FINDING), and per-input-type routing in §1 covering the common cases (issue, plan, tiny work, reviewed PR). Though code-free, this is an instruction-composition skill and its guidance is fully executable.

5 / 5

Workflow Clarity

A clear six-phase sequence (§1–§6) with explicit validation gates at each boundary — 'Do not start review without VALIDATION: GREEN', 'Wait until all selected review agents have finished', 'READY TO MERGE', and green CI on the final head — plus feedback loops for error recovery (review-correction mode, --verify-corrections re-review, CI-correction mode, REVIEW INCOMPLETE resolution).

5 / 5

Progressive Disclosure

No bundle files exist, and the single-file process document is cleanly sectioned with clearly signaled delegation to sibling skills (/prp-plan, /prp-implement, /prp-review). At roughly 70 lines, though, dense passages like the tiny-work rules in §1 and the disposition rules in §4 are candidates for a one-level-deep reference file, which keeps it at 'good structure with minor organization gaps' rather than the fully split anchor 5.

4 / 5

Total

18

/

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 the full lifecycle of what the skill does in concrete third-person terms, enumerates its accepted input types, and provides an explicit 'Always use when...' trigger clause with multiple natural phrasings. The only weaknesses are a couple of missing common trigger synonyms and slight breadth in the 'implement or ship end to end' phrasing that could overlap with simpler implementation skills.

DimensionReasoningScore

Specificity

The description enumerates concrete lifecycle actions — 'through planning, implementation, pull request, independent review, corrections, and green CI' — plus concrete input types ('an issue, PRD, document, existing plan, or free-form request'). This is comprehensive coverage of the workstream lifecycle with no meaningful gaps, matching the top anchor rather than the 'minor gaps' level 4 anchor.

5 / 5

Completeness

It explicitly answers both questions: 'what' as owning a workstream through planning, implementation, PR, review, corrections, and green CI, and 'when' via '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...'. The 'when' is explicit with multiple concrete trigger phrases, matching the level 5 anchor exactly; it is not merely 'present but could be more specific' (anchor 4).

5 / 5

Trigger Term Quality

Natural trigger phrases are present: 'implement or ship work end to end', 'take an issue or idea to a reviewed PR', 'run plan to PR', 'invokes /prp-issue'. Coverage is good but a few natural user phrasings (e.g., 'build this feature', 'deliver', 'close this issue') are absent, so it falls just short of the comprehensive-synonym anchor 5.

4 / 5

Distinctiveness Conflict Risk

Distinctive triggers like '/prp-issue', 'prp-orchestrate', and 'plan to PR' carve a clear orchestration niche, but the broad phrase 'implement or ship work end to end' keeps minor overlap risk with plain implementation/PR skills. It is more distinct than the 'somewhat specific but could overlap' level 3 anchor, but not the 'minimal conflict risk' of level 5.

4 / 5

Total

18

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

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.