spec-execution

Execute `specs/*.md` plans through working checkpoints. Use when the user says "execute this spec", "implement this plan", "run the spec", or points at a spec file.

Quality

89%

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

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.

The body is a well-sequenced, highly actionable multi-phase workflow with strong validation and feedback loops. It could improve by de-duplicating recurring guidance and splitting some material into reference files now that the skill is long.

Suggestions

Consolidate the commit-shape guidance and the 'ask only when product decision/destructive action/broad reshape/conflict' rule so each appears once, then reference it, to reduce repetition.

Move the sub-agent prompt template and anti-patterns into a reference file under references/ and link to it, improving progressive disclosure for a skill of this length.

Consider enumerating discrete capabilities (preflight, wave planning, execution, final review/ADR harvest) more explicitly in the description to lift specificity above 3.

Dimension	Reasoning	Score
Conciseness	Mostly lean and efficient, referencing other skills (git, standalone-commits, post-implementation-review) instead of re-explaining them, but the commit-shape guidance and the 'ask only when product decision/destructive/broad reshape' rule each recur multiple times, fitting the 'minor instances that could be trimmed' anchor 4 rather than the every-token-earns-its-place anchor 5.	4 / 5
Actionability	Provides concrete executable commands (bun typecheck, bun test, bun scripts/check-doc-hygiene.ts, git rm), copy-paste templates (wave plan, commit format, spec checkoff markdown), and specific response tables, matching the fully-executable anchor 5.	5 / 5
Workflow Clarity	Clear Phase 0-4 sequence with explicit validation checkpoints (type-check/tests after each wave, hygiene check at final review), feedback loops ('fix before moving on', 'Don't carry broken state'), and checklists (Preflight, Wave Planning), matching anchor 5; destructive ops (git rm spec) are guarded by verification so the batch/destructive cap does not apply.	5 / 5
Progressive Disclosure	Well-organized into clear sections with one-level-deep references to other skills and repo docs (specs/README.md, docs/adr/README.md), but for a complex skill all content lives inline in SKILL.md with no bundle files splitting sub-agent prompt templates or anti-patterns, fitting the good-structure anchor 4 rather than the split-and-signaled anchor 5.	4 / 5
	Total	18 / 20 Passed

Description

90%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 is strong: third-person voice, explicit what-and-when structure, and multiple concrete trigger phrases with synonyms. Its only soft spot is specificity, which lists one framed action rather than several discrete capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('spec execution') and a core action ('Execute specs/*.md plans through working checkpoints') but does not enumerate several specific actions, matching the '1-2 concrete actions, not comprehensive' anchor rather than the multi-action anchor 4.	3 / 5
Completeness	Explicitly answers both what ('Execute specs/*.md plans through working checkpoints') and when ('Use when the user says...') with concrete trigger phrases, matching anchor 5.	5 / 5
Trigger Term Quality	Provides comprehensive natural trigger synonyms users would say ('execute this spec', 'implement this plan', 'run the spec') plus the file-pointing trigger, matching the comprehensive-synonyms anchor 5.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (executing spec/plan files) with distinct, spec-anchored triggers and minimal overlap with other skills, matching the clear-niche anchor 5.	5 / 5
	Total	18 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/spec-execution/SKILL.md
Commit: abe10f3

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.