implement

Use when the user asks to execute an existing task plan's Solution under TDD — RED → GREEN → REFACTOR → CHECK per AGENTS.md. Requires a written plan resolved through the `tasks` role in AGENTS.md. Do NOT trigger on planning, reviewing committed changes, or fixing pre-existing failing tests outside a plan.

Quality

86%

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

81%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.

A highly actionable, well-sequenced TDD workflow with strong validation and feedback loops. The main weakness is redundancy between the Overview and Rules and a formatting glitch in step 6.

Suggestions

Remove the overlap between the Overview and Rules 3-4 (e.g. drop the 'never edit a failing test / never silence lint' sentences from the Overview since they are fully stated in the Rules) to tighten token use.

Fix the step 6 heading ('6. **6. **TOTAL STOP**') duplicated-numbering/bolding glitch.

Consider moving the nine Rules into a separate references file (e.g. RULES.md) referenced one-level-deep from the body, which would let progressive_disclosure reach the cleanly-split 5 anchor.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and assumes Claude's intelligence (no explaining of what TDD or tests are), but the Overview restates prohibitions ('never edit a failing test', 'never silence lint') that are repeated verbatim in Rules 3-4, and step 6 has a duplicated-numbering formatting glitch, so it could be tightened below the 4 anchor.	3 / 5
Actionability	Fully executable guidance: a concrete check-command detection table (deno task check, npm run check, make check, pytest, go vet), named todo tools, and specific suppression patterns to avoid (// deno-lint-ignore, eslint-disable, # noqa) covering the common cases.	5 / 5
Workflow Clarity	A clear 6-step sequence with explicit validation checkpoints (RED must fail, CHECK must exit 0, re-run tests after refactor, final whole-project check, git-status and scope-creep checks), feedback loops (stop-on-second-fix-failure with STOP-ANALYSIS REPORT), and a verification checklist.	5 / 5
Progressive Disclosure	Well-organized into Overview, Context, Rules, Instructions, and Verification sections with clear one-level references to AGENTS.md, but it is a dense ~75-line monolith with all nine rules inlined and no bundle files, leaving minor organization gaps short of the cleanly-split 5 anchor.	4 / 5
	Total	17 / 20 Passed

Description

92%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, concrete description that states what it does, when to use it, and when not to trigger, with a clear TDD niche. Only slight weakness is missing natural synonyms like 'implement'.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'execute an existing task plan's Solution under TDD' with the explicit 'RED → GREEN → REFACTOR → CHECK' cycle — giving comprehensive coverage of what the skill does, matching the comprehensive-coverage anchor rather than the 4 anchor's 'minor gaps'.	5 / 5
Completeness	Explicitly answers both what ('execute an existing task plan's Solution under TDD — RED → GREEN → REFACTOR → CHECK') and when via a clear 'Use when...' clause plus 'Do NOT trigger on...' negative triggers, matching the explicit-what-and-when anchor.	5 / 5
Trigger Term Quality	Good keyword coverage with natural terms ('execute', 'task plan', 'TDD', 'planning', 'reviewing committed changes', 'fixing pre-existing failing tests') plus negative triggers, but missing common synonyms such as 'implement' or 'build the plan', so it is not the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	Clear niche (Implement Phase of the task lifecycle under TDD) with explicit negative triggers excluding planning, reviewing committed changes, and fixing pre-existing tests, giving minimal conflict risk.	5 / 5
	Total	19 / 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: korchasa/flowai-plugins
Path: plugins/flowai/skills/implement/SKILL.md
Commit: b4ba256

Reviewed: ~22 hours 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.