prp-deliver

This is an experimental skill. Never use it unless the user explicitly tells you to invoke $prp-deliver.

Quality

58%

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-deliver/SKILL.md

Quality

Content

96%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 a tightly written, highly actionable orchestration workflow with clear sequencing, explicit validation gates, and feedback loops throughout. Its only soft spot is progressive disclosure: everything is inline with no extracted reference material, which is acceptable for a self-contained orchestration skill but leaves minor organization headroom.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural with no padding or explanation of concepts Claude already knows, and it assumes competence by referencing sibling skills without defining them, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	It provides concrete, copy-paste-ready agent-invocation prompt templates with explicit return contracts (VALIDATION: GREEN, absolute paths, PR URL, verdict), matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	Six stages are clearly sequenced with explicit entry/exit validation gates and feedback loops (correct→re-review until READY TO MERGE; CI failure→implement→fresh review), matching the 'clear sequence with explicit validation and feedback loops' anchor.	5 / 5
Progressive Disclosure	Self-contained and well-sectioned into six numbered stages with no bundle files to reference, but at ~66 lines it exceeds the simple-skill threshold and keeps all prompt templates inline, leaving minor organization gaps versus the 'clear overview with one-level-deep references' anchor 5.	4 / 5
	Total	19 / 20 Passed

Description

20%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 functions as a safety guard rather than a capability description: it states no 'what' and only a tautological 'when', with a technical command token instead of natural triggers. Its one strength is conflict-risk reduction via the explicit-invocation gate.

Suggestions

Add a 'what' clause naming the concrete capability, e.g. 'Delivers one outcome from source input to a published READY TO MERGE PR review and green CI by orchestrating plan, implement, review, and correction agents.'

Add natural trigger terms users would actually say, such as 'deliver', 'ship a reviewed PR', 'take an issue to merge-ready', alongside the existing invocation guard.

Keep the experimental/guard notice but move it after a concrete capability and trigger clause so the description still answers both 'what' and 'when'.

Dimension	Reasoning	Score
Specificity	The description names no concrete actions or domain — 'This is an experimental skill' is a guard statement, not a capability description, matching the 'entirely vague; no concrete actions' anchor.	1 / 5
Completeness	A 'when' clause is present but tautological ('unless the user explicitly tells you to invoke $prp-deliver') and the 'what' is entirely missing, matching the 'only when present without what' anchor; not 1 because a when clause is explicitly stated.	2 / 5
Trigger Term Quality	The only token is the technical command name '$prp-deliver'; there are no natural keywords a user would say when they need this skill, matching the 'no natural keywords; only technical jargon' anchor.	1 / 5
Distinctiveness Conflict Risk	The explicit-invocation guard makes wrong-skill triggering near-impossible (low conflict risk), but no niche or trigger phrase is described, so it stops short of the 'clear niche' anchor 5.	4 / 5
	Total	8 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Wirasm/prp
Path: .agents/skills/prp-deliver/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.