speckit-implement

Execute the implementation plan by processing and executing all tasks defined in tasks.md

Quality

53%

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

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/speckit-implement/SKILL.md

Quality

Content

60%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 exceptionally actionable with concrete commands, named tools, and ready-to-use templates, and the main workflow is well-sequenced with validation gates. Its weaknesses are verbosity and monolithic structure: large reference tables and the entire Trello integration guide are inlined rather than split into one-level-deep reference files.

Suggestions

Move the per-technology and tool-specific ignore-pattern tables into a references/ file (e.g. IGNORE-PATTERNS.md) and link to it, cutting the main body substantially.

Extract the Trello Integration section (§§ A-E) into a references/ file and reference it from the Outline steps that depend on it.

De-duplicate the before/after-implement hook blocks by stating the shared rules once and parameterizing only the differing key name and labels.

Dimension	Reasoning	Score
Conciseness	The ~360-line body inlines large reference tables (per-technology ignore patterns, tool-specific patterns) and near-duplicate before/after-implement hook instructions that belong in separate files, matching 'noticeably verbose; several padded sections'; it avoids a 1 because it does not lecture on concepts Claude already knows.	2 / 5
Actionability	It gives fully executable guidance — exact shell commands ('check-prerequisites.sh --json --require-tasks --include-tasks', 'git rev-parse --abbrev-ref HEAD'), named MCP tools, and copy-paste comment templates with explicit placeholders — covering the common cases, matching the 'fully executable; copy-paste ready' anchor.	5 / 5
Workflow Clarity	The Outline is a clearly numbered 1-10 sequence with validation gates (checklist STOP-and-ask, completion validation), fitting 'clear sequence with most checkpoints'; it stays below 5 because the per-phase 'Verify each phase completion' checkpoint is generic rather than an explicit validate-then-fix feedback loop.	4 / 5
Progressive Disclosure	With no references/scripts/assets bundle present, everything is monolithically inlined — the Trello Integration section and the ignore-pattern reference tables are exactly content that 'clearly belongs in separate files' but is inlined, matching the 2 anchor; internal '§ A/§ B' anchors are not external file references, so it cannot reach 3.	2 / 5
	Total	13 / 20 Passed

Description

46%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 states a clear purpose tied to spec-kit's tasks.md but omits any 'Use when...' trigger guidance and relies on technical jargon rather than natural user phrases. This caps completeness and trigger-term quality at the midpoint, leaving it a moderately specified but poorly triggered skill.

Suggestions

Add an explicit 'Use when...' trigger clause naming natural phrases a user would say (e.g. 'Use when implementing a spec-kit feature, running tasks.md, or executing the implementation plan').

Replace or augment the jargon ('implementation plan', 'tasks.md') with user-facing synonyms to broaden trigger coverage.

List a couple more concrete actions (e.g. 'run checklists, execute phases, sync Trello') to lift specificity above a 3.

Dimension	Reasoning	Score
Specificity	Names the domain ('implementation plan', 'tasks.md') and two concrete actions ('processing and executing all tasks'), matching the 'names domain and 1-2 concrete actions' anchor; it stops short of the comprehensive multi-action coverage of a 4.	3 / 5
Completeness	It has a clear 'what' ('Execute the implementation plan by processing and executing all tasks defined in tasks.md') but no 'Use when...' trigger, so per the missing-trigger cap it cannot exceed 3; a 4 would require an explicit if imperfect 'when' clause.	3 / 5
Trigger Term Quality	The only keywords are technical jargon ('implementation plan', 'tasks', 'tasks.md'); it lacks the natural phrases a user would actually say, fitting the 'one or two generic keywords; missing natural phrases' anchor rather than the 3 which requires some relevant natural terms.	2 / 5
Distinctiveness Conflict Risk	Tying execution to spec-kit's 'tasks.md' gives it a fairly distinct niche with only minor overlap against generic implementation skills; it is not a 5 because 'execute the implementation plan' is still broadly applicable phrasing.	4 / 5
	Total	12 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: g14wx/staffSync
Path: .claude/skills/speckit-implement/SKILL.md
Commit: 682bfbc

Reviewed: 1 day 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.