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

83%

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

77%

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

A strong, actionable orchestration workflow with excellent sequencing, verification checkpoints, and concrete commands. Its weaknesses are verbosity from repeated guidance across sections and a lack of progressive disclosure — everything lives inline in one long file.

Suggestions

Consolidate the commit-shape guidance into one section and reference it from the others to reduce repetition and tighten conciseness toward 3.

Move the wave-planning template, sub-agent prompt checklist, and anti-patterns into a single `references/` file (e.g. `references/wave-planning.md`) and link to it from SKILL.md to add one-level-deep progressive disclosure.

De-duplicate the parallel-vs-sequential reasoning so it lives in one table rather than being restated across Phase 2, Phase 3, and Sub-Agent Prompts.

Dimension	Reasoning	Score
Conciseness	The guidance is mostly efficient and assumes Claude's competence, but it is ~260 lines with redundancy: commit-shape advice recurs in the intro, Phase 3.4, and Phase 4.5, and the parallel/sequential reasoning is restated across Phase 2, Phase 3, and the Sub-Agent Prompts section. Not a 1 because it avoids explaining basic concepts, not a 3 because it could be meaningfully tightened.	2 / 3
Actionability	It gives concrete executable commands (`bun typecheck`, `bun test`, `bun scripts/check-doc-hygiene.ts`, `git rm`), a copy-paste commit format, spec checkbox examples, and decision tables — fully actionable guidance even without heavy code.	3 / 3
Workflow Clarity	The skill is a clearly sequenced phase loop (Preflight → Read → Plan Waves → Execute/Verify → Final Review) with explicit validation checkpoints, feedback loops ('If verification fails, fix issues before proceeding. Don't carry broken state'), and an error-recovery table.	3 / 3
Progressive Disclosure	Sections are well-organized into clear phases, but the skill is a single 260-line monolithic SKILL.md with no bundle files or external references. Because it exceeds the simple-skill threshold and keeps content that could be split (wave templates, sub-agent prompt guidance, anti-patterns) inline, it sits at the anchor 2 'content that should be separate is inline' rather than 3.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 well-formed description: it states a concrete capability and supplies explicit, natural trigger phrasings tied to a distinctive spec-execution niche. The only soft spot is specificity, which names one action rather than enumerating several concrete operations.

Suggestions

Optionally enumerate the concrete operations the skill performs (e.g., 'plans implementation waves, launches sub-agents, verifies checkpoints, and harvests decisions to ADRs') to lift specificity to 3.

Dimension	Reasoning	Score
Specificity	Names the domain ('specs/*.md plans') and a concrete action ('Execute ... through working checkpoints'), but it lists a single action rather than multiple distinct concrete actions, so it falls short of the anchor 3 example.	2 / 3
Completeness	It answers both what ('Execute specs/*.md plans through working checkpoints') and when (explicit 'Use when...' trigger clause), satisfying the highest anchor; it is not a 2 because the trigger guidance is explicit rather than implied.	3 / 3
Trigger Term Quality	The clause "Use when the user says 'execute this spec', 'implement this plan', 'run the spec', or points at a spec file" gives natural, varied phrasings a user would actually say, matching the good coverage anchor.	3 / 3
Distinctiveness Conflict Risk	The spec-file execution niche and file/phrase-based triggers are unlikely to fire for unrelated skills, matching the clear-niche anchor and not the overlapping anchor 2.	3 / 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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: EpicenterHQ/epicenter
Path: .agents/skills/spec-execution/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.