implement

Research, implement, test, document, and review a Fallow feature, fix, refactor, or repository improvement. Use when asked to build or change Fallow.

Quality

86%

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

Quality

Content

86%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 tight, well-organized procedural overview with strong conciseness and clean progressive disclosure through one-level-deep doc references. The main gaps are in actionability and workflow_clarity, where a few steps defer specifics to external docs and the review retry loop is implicit.

Suggestions

Spell out the 'pipeline order' referenced in step 6 (or link to its definition) so the implementation sequence is unambiguous without opening another doc.

Make the review feedback loop explicit in step 8: run reviewers → if blocks, fix and re-run until clean, mirroring the validate→fix→retry pattern.

Name the most common gates inline in step 7 (e.g., lint, typecheck, tests) so the action is executable before consulting quality-gates.md.

Dimension	Reasoning	Score
Conciseness	A lean nine-step procedure with concrete file references and no padding — it assumes Claude's competence and every line earns its place, matching the 'lean and efficient' anchor. No concept over-explanation is present.	5 / 5
Actionability	Concrete file pointers (AGENTS.md, docs/development/quality-gates.md, .plans/<task>.md) make the procedure actionable, but several steps defer executable detail to referenced docs and 'Implement in pipeline order' leaves the actual sequence undefined. Not a 5 because the common-case specifics are not inline.	4 / 5
Workflow Clarity	Nine steps are clearly sequenced with validation checkpoints (gates in step 7, reviewers in step 8, verification evidence in step 9). Not a 5 because the feedback loop is only implicit — 'Resolve every block' does not spell out the fix-and-re-run cycle that the anchor requires.	4 / 5
Progressive Disclosure	A short overview that pushes detail into one-level-deep, clearly signaled inline references (docs/README.md, task-context-map.md, quality-gates.md, review-routing.md), with content appropriately split. No bundle files exist, and the skill is well under 50 lines and cleanly organized.	5 / 5
	Total	18 / 20 Passed

Description

87%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 concise, well-structured description that explicitly covers what the skill does and when to use it, scoped clearly to the Fallow project. Trigger phrasing and distinctiveness are strong; only synonym/term breadth keeps it from a perfect mark.

Dimension	Reasoning	Score
Specificity	Lists five concrete action verbs ('Research, implement, test, document, and review') and four object types ('feature, fix, refactor, or repository improvement'), giving broad lifecycle coverage. Not a 5 because the verbs are generic process actions rather than tool-specific operations like the anchor's 'extract text, fill forms, merge documents'.	4 / 5
Completeness	Clearly answers both what ('Research, implement, test, document, and review a Fallow feature, fix, refactor, or repository improvement') and when ('Use when asked to build or change Fallow') with a concrete trigger phrase. The 'Use when' clause is present, so the completeness cap does not apply.	5 / 5
Trigger Term Quality	The explicit 'Use when asked to build or change Fallow' supplies natural user phrasing ('build', 'change'). Not a 5 because synonym coverage is thin — natural variations like 'add a feature', 'fix a bug', or 'refactor' are absent.	4 / 5
Distinctiveness Conflict Risk	Scoping to the named project 'Fallow' in both the capability and trigger ('build or change Fallow') carves out a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	18 / 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: fallow-rs/fallow
Path: .claude/skills/implement/SKILL.md
Commit: 03aad8c

Reviewed: 2 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.