post-implementation-review

Hub for the broad post-implementation review and second-read pass after an implementation: list every touched file as an ASCII tree, mentally inline helpers, audit dead paths and stale imports, name invariant owners, sanity-check API shape and naming, and delegate to focused review skills as needed. Use after finishing an implementation, before final response, or when the user says 'post-implementation review', 'review what you just did', 'second pass', or 'final sweep'.

Quality

96%

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

Quality

Content

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

An excellent, densely actionable review hub: terse checklists, a sequenced workflow with a real validation checkpoint, and clean progressive disclosure through one-level references to sibling skills. No dimension scored below the top anchor.

Dimension	Reasoning	Score
Conciseness	Lean, terse imperative prose with structured .txt checklists; it never explains concepts Claude already knows and every section is skill-specific guidance that earns its place, matching the 'lean and efficient; every token earns its place' anchor.	3 / 3
Actionability	Instruction-only but concrete: specific ownership questions, an enumerated smell checklist, an ASCII-tree evidence format, and a copy-paste 'Output Shape' template give specific, actionable guidance rather than vague direction.	3 / 3
Workflow Clarity	A clear 9-step 'Review Order' with an explicit validation checkpoint — step 8: 'Reproduce any failure on clean HEAD before blaming the change; separate pre-existing red from regressions you introduced' — matching the 'clear sequence with explicit validation steps' anchor.	3 / 3
Progressive Disclosure	Well-organized into focused sections with clearly signaled one-level-deep references to sibling skills (../fresh-context-review/SKILL.md, ../radical-options/SKILL.md); as a hub it appropriately delegates detail to focused skills rather than inlining it.	3 / 3
	Total	12 / 12 Passed

Description

92%

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, specific description with explicit trigger phrasing and a clear what/when structure. Its only weakness is conflict risk: as a hub it deliberately overlaps with many sibling review skills, and 'review what you just did' is generic enough to fire for the wrong review skill.

Suggestions

Tie the 'review what you just did' trigger explicitly to the just-completed implementation (e.g., 'review the implementation you just finished') so it is less likely to collide with diff/design review skills like fresh-context-review.

Lead with the distinguishing scope — a broad second-read over the whole touched surface after implementation — before the action list, so the hub-vs-focused-skill choice is unambiguous at a glance.

Consider a negative trigger ('not for first-read confusion or a single focused smell — start there instead') to sharpen the boundary against first-read-review and the focused skills it delegates to.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'list every touched file as an ASCII tree, mentally inline helpers, audit dead paths and stale imports, name invariant owners, sanity-check API shape and naming' — matching the 'lists multiple specific concrete actions' anchor.	3 / 3
Completeness	Answers both what (the enumerated review actions) and when with an explicit 'Use after finishing an implementation, before final response, or when the user says…' clause, matching the 'clearly answers both what AND when' anchor.	3 / 3
Trigger Term Quality	Includes natural phrases a user would say — "'post-implementation review', 'review what you just did', 'second pass', or 'final sweep'" — giving good coverage of natural trigger terms rather than jargon.	3 / 3
Distinctiveness Conflict Risk	It is a 'Hub' that explicitly overlaps with ~10 sibling review skills (first-read-review, fresh-context-review, code-audit, refactoring), and 'review what you just did' is broad enough to collide with them; not the level-3 'clear niche with distinct triggers' because the review space is crowded.	2 / 3
	Total	11 / 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: 2 suspicious	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/post-implementation-review/SKILL.md
Commit: cb12bcc

Reviewed: 3 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.