speckit-implement

Execute all tasks from the task breakdown to build the feature. Use after task generation to systematically implement the planned solution following TDD approach where applicable.

Quality

72%

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

Fix and improve this skill with Tessl

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

Quality

Content

77%Weight 40%Scale 1-3

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 well-sequenced, highly actionable instruction skill with explicit validation checkpoints and feedback loops, but it is bloated by inline per-technology ignore-pattern catalogs that restate common knowledge and should live in a separate reference file.

Suggestions

Move the per-technology and tool-specific ignore-pattern tables into a references file (e.g. references/ignore-patterns.md) and reference it from step 4 to reduce inline bulk and token cost.

Add a verification checkpoint to step 4 (e.g. confirm each created ignore file contains the required patterns before proceeding) so the project-setup phase matches the validation rigor of steps 2, 8, and 9.

Trim restatements of well-known concepts (e.g. explanations of what each technology's build artifacts are) to assume Claude's competence and tighten conciseness toward the score-3 anchor.

Dimension	Reasoning	Score
Conciseness	The workflow steps are mostly efficient and well-organized, but the large per-technology and tool-specific ignore-pattern catalogs restate common .gitignore knowledge Claude already has, adding padding that keeps it from the lean score-3 level while staying above the verbose score-1 level.	2 / 3
Actionability	It provides concrete commands (e.g. `check-prerequisites.ps1 -Json -RequireTasks -IncludeTasks`, `git rev-parse --git-dir`), exact matchers (`- [ ]`, `- [X]`), a defined status-table format, and explicit mark-task-`[X]` instructions, giving copy-paste-ready guidance; it is not at 2 because the directions are specific and executable rather than pseudocode.	3 / 3
Workflow Clarity	A clear 9-step sequence includes explicit validation checkpoints and feedback loops: step 2 counts checklists, halts on incomplete items, and gates on a yes/no response; step 8 halts on failed non-parallel tasks while continuing parallel ones; step 9 runs completion validation. This matches the score-3 anchor with feedback loops for error recovery.	3 / 3
Progressive Disclosure	No bundle files (references/, scripts/, assets/) are present, and while the body is organized by headings, the extensive per-technology ignore-pattern tables are inline reference material that would be better split into a separate file, matching the score-2 anchor of structure with content that should be separate kept inline.	2 / 3
	Total	10 / 12 Passed

Description

67%Weight 40%Scale 1-3

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 answers both what and when with an explicit trigger and a recognizable spec-kit/TDD niche, but its actions stay abstract and its natural-language trigger terms are limited. It reads as a competent but slightly generic implementation trigger.

Suggestions

Add concrete action verbs and artifacts a user would name, e.g. "run task breakdowns, scaffold features, and write tests" instead of the abstract "implement the planned solution".

Broaden natural trigger terms to include phrasings users actually say, such as "Use when implementing a spec-kit feature, executing tasks.md, or starting TDD work after task generation".

Sharpen distinctiveness by leading with the spec-kit/TDD scope so it cannot be confused with general coding skills.

Dimension	Reasoning	Score
Specificity	Phrases like "Execute all tasks", "build the feature", "implement the planned solution", and "following TDD approach" name the domain and several actions, but the actions are abstract rather than concrete operations, so it is not comprehensive (score 3) yet more than vague (score 1).	2 / 3
Completeness	It clearly answers "what" ("Execute all tasks from the task breakdown to build the feature... implement the planned solution") and "when" ("Use after task generation"), with an explicit trigger clause, matching the score-3 anchor; it is not capped at 2 because the when is explicit, not merely implied.	3 / 3
Trigger Term Quality	The explicit trigger "Use after task generation" plus terms "implement", "task", and "TDD" give some relevant keywords, but common natural variations a user would say (e.g. "spec", "execute tasks", "implementation") are missing, so it stops at 2 rather than reaching full coverage at 3.	2 / 3
Distinctiveness Conflict Risk	Tying the skill to "task breakdown", "spec-kit project structure", and "TDD approach" gives it a recognizable niche, but "implement the planned solution" is generic enough to overlap with other implementation skills, so it is somewhat specific rather than clearly distinct at 3.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: foryourhealth111-pixel/Vibe-Skills
Path: bundled/skills/speckit-implement/SKILL.md
Commit: f627ab5

Reviewed: 11 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.