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 lean, well-structured procedural skill: the numbered lifecycle is clearly sequenced with validation gates, and detail is properly pushed to referenced project docs. The main gaps are a few non-executable step directives and error-recovery loops that are implied rather than spelled out.

Suggestions

For step 6, include the concrete commands for creating the branch and opening the pull request (e.g., the exact git/gh invocations used in this repo) so the step is executable without inference.

Add an explicit feedback loop after steps 8-9, e.g., "If a gate or reviewer blocks, fix and re-run that gate before updating the pull request," so error recovery is not merely implied by "Resolve every block."

Dimension	Reasoning	Score
Conciseness	The ~30-line body is purely procedural with no concept explanations or padding ("Write the acceptance criteria and verification plan to the gitignored `.plans/<task>.md`"); every line earns its place and it delegates detail to external docs.	5 / 5
Actionability	Most steps are actionable via concrete pointers ("`--format json --quiet`", "run `panel-review`", named doc paths, `.plans/<task>.md`), but several steps remain directives without executable commands ("Create an implementation branch and ready pull request"), leaving minor gaps per the anchor-4 example.	4 / 5
Workflow Clarity	A clear 10-step sequence with validation checkpoints ("get a command that fails before you change code", "Run every applicable gate", "Resolve every block"), but error-recovery loops are implied rather than explicit — no stated fix-and-re-run cycle if a gate or reviewer blocks.	4 / 5
Progressive Disclosure	The skill is under 50 lines with no bundle files, and it delegates all detail to well-signaled one-level-deep external references (`docs/development/quality-gates.md`, `docs/development/review-routing.md`, `docs/development/task-context-map.md`), matching the short-skill anchor for a top score.	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 strong description: it enumerates concrete lifecycle actions, explicitly states both what it does and when to use it, and is tightly scoped to the Fallow project. The only weakness is slightly thin trigger-term coverage (missing natural synonyms such as "add" or "update").

Dimension	Reasoning	Score
Specificity	"Research, implement, test, document, and review" lists several specific lifecycle actions over a named domain ("a Fallow feature, fix, refactor, or repository improvement"), but the actions are stage-level verbs rather than concrete operations, leaving minor gaps versus the comprehensive anchor.	4 / 5
Completeness	The description explicitly answers both questions: 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 matching the anchor-5 good examples.	5 / 5
Trigger Term Quality	"build or change Fallow" plus "feature, fix, refactor" are natural phrases a user would say, but common synonyms like "add", "update", or "make a change" are missing, so coverage is good rather than comprehensive.	4 / 5
Distinctiveness Conflict Risk	The scope is tightly bound to a single named project ("Fallow") and the trigger ("asked to build or change Fallow") is distinct, giving a clear niche with minimal conflict 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: .agents/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.