speckit-implement

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

Quality

56%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

62%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 content is a thorough, well-sequenced implementation workflow with strong validation and error-handling loops, but it is bloated by inlined reference data (13-language ignore patterns) and duplicated hook-handling logic. Splitting reference material into bundle files and de-duplicating the hook sections would materially improve it.

Suggestions

Move the per-language and tool-specific ignore-pattern tables into a references/ bundle file (e.g. IGNORE-PATTERNS.md) and link to it from step 4.

De-duplicate the extension-hook handling: define it once and have step 10 reference the pre-execution section instead of repeating the near-verbatim block.

Tighten descriptive steps like step 7's "Implement models, services, CLI commands, endpoints" into concrete, actionable sub-steps or delegate to tasks.md parsing.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: it inlines ignore-pattern tables for 13 languages that read as reference data, and the extension-hook logic is duplicated near-verbatim in both "Pre-Execution Checks" and step 10, creating padded sections that could be tightened.	2 / 5
Actionability	Guidance is largely executable — concrete commands (e.g. `check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks`), file paths, checklist regexes, and table formats — with only minor gaps where steps are descriptive ("Implement models, services, CLI commands").	4 / 5
Workflow Clarity	The 10-step outline is clearly sequenced with explicit validation checkpoints (checklist PASS/FAIL table, completion validation in step 9) and feedback loops (halt on failed non-parallel tasks, STOP-and-ask on incomplete checklists), matching the 5 anchor.	5 / 5
Progressive Disclosure	Section headers and a numbered outline provide structure, but no bundle files exist and the large per-language ignore-pattern reference is inlined in SKILL.md rather than split into a reference file, fitting the 3 anchor.	3 / 5
	Total	14 / 20 Passed

Description

50%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 in third person and references a concrete file, but it is generic in its verbs and lacks any "Use when" trigger guidance. It is functional but would benefit from explicit invocation triggers and more specific action language.

Suggestions

Add a "Use when..." clause naming concrete triggers, e.g. "Use when implementing a spec-kit project after tasks.md has been generated."

Replace generic verbs ("processing and executing") with more specific actions like "run setup, test, core, integration, and polish phases defined in tasks.md".

Include natural trigger terms users would say (e.g. "implement the plan", "run the tasks", "execute tasks.md") to improve distinctiveness.

Dimension	Reasoning	Score
Specificity	"Execute the implementation plan by processing and executing all tasks defined in tasks.md" names the domain plus two concrete actions (processing, executing tasks) and a concrete artifact (tasks.md), but the verbs are generic and not comprehensive, matching the 3 anchor.	3 / 5
Completeness	The description gives a clear "what" (execute the implementation plan / run all tasks in tasks.md) but includes no "Use when..." clause or equivalent trigger guidance, so per the rubric cap completeness is held at 3.	3 / 5
Trigger Term Quality	Natural terms like "implementation plan", "tasks", and "tasks.md" are present but limited; common synonyms or variations a user might say are missing, fitting the 3 anchor rather than the broader coverage of 4.	3 / 5
Distinctiveness Conflict Risk	The tasks.md reference ties it to the spec-kit workflow, but with no explicit trigger phrase it could still overlap with generic implement/execute skills, matching the 3 anchor rather than the more distinct 4.	3 / 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: unoplatform/uno
Path: .claude/skills/speckit-implement/SKILL.md
Commit: eaa505e

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.