implement

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

Quality

81%

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

82%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.

The body is a tight, well-sequenced procedural workflow that respects Claude's competence and routes detail to indexed docs via one-level-deep references. Its main limitation is actionability that leans on external doc pointers rather than inline, copy-paste-ready specifics for gates and reviews.

Suggestions

Inline one or two of the most common gate/reviewer commands (or a concrete example of running them) so the skill is executable without first reading the external docs.

Group the referenced docs under a short "References" section so navigation is explicit rather than spread across numbered steps.

Dimension	Reasoning	Score
Conciseness	The body is a lean ~22-line procedural list with one action per step and no padding or concept explanation Claude already knows (e.g. "Use apply_patch for edits", "Preserve unrelated work"). Every token earns its place; not lower because there is no verbosity to trim.	5 / 5
Actionability	Concrete file pointers (AGENTS.md, docs/development/task-context-map.md, quality-gates.md, review-routing.md) and explicit directives ("run panel-review", "Use apply_patch") give mostly executable guidance. Not a 5 because many steps defer specifics to external docs rather than giving copy-paste-ready commands, and not a 3 because the named artifacts and tool directives are genuinely actionable.	4 / 5
Workflow Clarity	A clearly sequenced 9-step lifecycle with validation checkpoints ("Run every applicable gate", "Resolve every block", "Run the reviewer set") and feedback-loop language for review. Not a 5 because validation specifics are delegated to external docs rather than stated inline, leaving minor checkpoint gaps; not a 3 because checkpoints are explicitly present and ordered.	4 / 5
Progressive Disclosure	No bundle files exist under references/scripts/assets, and the body uses well-signaled one-level-deep references to indexed docs (AGENTS.md, docs/development/*.md) rather than nesting. Good structure with minor gaps: references are scattered as inline paths rather than organized into a dedicated navigation section. Not a 5 due to that organizational gap, not a 3 because references are clearly signaled and single-level.	4 / 5
	Total	17 / 20 Passed

Description

80%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.

The description is concise, third-person, and clearly answers both what the skill does and when to use it, with concrete action verbs and an explicit trigger clause. Its main weakness is limited trigger-term variety, relying on a single "Use when asked to build or change Fallow" phrasing.

Suggestions

Broaden trigger-term coverage with synonyms users naturally say, e.g. "Use when asked to build, modify, fix, refactor, or improve Fallow."

Consider mentioning common file/work artifacts (e.g. feature, bugfix, PR, repo improvement) as trigger keywords to improve natural-phrase matching.

Dimension	Reasoning	Score
Specificity	"Research, implement, test, document, and review" lists five concrete actions scoped to a Fallow change, but stops short of exhaustive sub-action coverage. Not a 5 because the actions are somewhat generic verbs without deeper concrete detail; not a 3 because five distinct specific actions clearly exceed naming the domain alone.	4 / 5
Completeness	It explicitly states the "what" (research, implement, test, document, review a Fallow feature/fix/refactor) and the "when" ("Use when asked to build or change Fallow") with a concrete trigger phrase. Both halves are present and explicit, matching the top anchor; not lower because neither half is missing or merely implied.	5 / 5
Trigger Term Quality	"Use when asked to build or change Fallow" gives one natural trigger phrase but offers few synonyms or natural variations users might say. Not a 4 because common phrasings like "feature", "fix", "refactor" are present only as objects rather than as trigger keywords, and not a 2 because at least one natural user phrase is present.	3 / 5
Distinctiveness Conflict Risk	Scoping to "Fallow" plus explicit build/change triggers carves a clear niche with minimal overlap against general skills. Not lower because the trigger is product-specific and unlikely to fire for unrelated 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: 7e1e075

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.