implement

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

Quality

83%

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

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.

An exemplarily tight procedural skill: a numbered lifecycle with genuine validation gates, fail-first bug discipline, and detail correctly pushed out to referenced repo docs. The only gaps are a few underspecified steps and the absence of section headers for navigation.

Dimension	Reasoning	Score
Conciseness	The ~38-line body is lean and imperative with zero concept explanations ("Read AGENTS.md...", "Run every applicable gate from docs/development/quality-gates.md"); every line carries a distinct instruction and assumes Claude's competence.	5 / 5
Actionability	Most steps name concrete artifacts and commands (`.plans/<task>.md`, `--format json --quiet`, `panel-review`, specific docs paths), but a few remain directional ("Implement in pipeline order", "Resolve every block") without the specific commands those steps would invoke.	4 / 5
Workflow Clarity	A clear 10-step sequence with explicit validation checkpoints: plan-before-edit (steps 3-4), branch/PR before tracked edits (step 6), fail-first bug reproduction ("get a command that fails before you change code"), gates (step 8), and a resolve-every-block recovery loop (step 9).	5 / 5
Progressive Disclosure	No bundle files exist, so the body correctly stays self-contained while delegating detail to real repo docs via clearly signaled, one-level-deep backticked paths (quality-gates.md, task-context-map.md, review-routing.md). It lacks section headers that would make the procedure easier to navigate, keeping it just short of the top anchor.	4 / 5
	Total	18 / 20 Passed

Description

78%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, third-person description that pairs a five-verb capability list with an explicit 'Use when' trigger and a clearly bounded domain. It is concise and distinct; the only room to grow is broadening natural trigger synonyms.

Suggestions

Widen the 'when' clause to echo the change types users actually name, e.g. 'Use when asked to build, fix, refactor, or improve anything in the Fallow repository.'

Add one or two natural synonyms (e.g. 'bug', 'add', 'improve') to the trigger keywords so the description matches how users phrase ad-hoc change requests.

Dimension	Reasoning	Score
Specificity	The description lists several specific actions ("Research, implement, test, document, and review") applied to concrete object types ("feature, fix, refactor, or repository improvement"), but the verbs are workflow-level rather than operationally concrete like "extract text and tables" or "fill forms", leaving minor coverage gaps.	4 / 5
Completeness	Both parts are present: a clear 'what' ("Research, implement, test, document, and review a Fallow feature, fix, refactor...") and an explicit 'when' ("Use when asked to build or change Fallow"). The 'when' clause could be slightly more specific by mirroring the full range of change types.	4 / 5
Trigger Term Quality	It includes natural phrases a user would say — "build or change", "feature", "fix", "refactor" — but misses common synonyms such as "add", "bug", or "improve" that would round out keyword coverage.	4 / 5
Distinctiveness Conflict Risk	The description is anchored to a distinct niche ("a Fallow feature, fix, refactor, or repository improvement") with a scoped trigger ("asked to build or change Fallow"), giving it minimal overlap with other skills.	5 / 5
	Total	17 / 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: 74177e5

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.