speckit-plan

Execute the implementation planning workflow using the plan template to generate design artifacts.

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

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

Quality

Content

75%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 an efficient, well-structured procedural workflow with concrete commands, file paths, and explicit validation checkpoints across phases. Its main weakness is the near-verbatim duplication of the extension-hooks procedure, which bloats the token budget and slightly hurts organization.

Suggestions

Factor the repeated before_plan/after_plan hook procedure into a single shared sub-procedure and reference it from both check points to remove the ~30-line duplication.

Tighten the research-agent dispatch into concrete, executable instructions rather than templated 'Task: Research {unknown}...' pseudocode.

Add an explicit fix-and-retry feedback loop for gate/Constitution failures instead of only emitting 'ERROR' and stopping.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural with no concept-padding and assumes Claude's competence, but the extension-hooks procedure (~30 lines) is duplicated nearly verbatim for before_plan and after_plan and could be factored into a shared reference.	4 / 5
Actionability	It gives concrete commands (setup-plan.ps1 -Json), exact paths, markers, output templates, and a quote-escape syntax, but the research-agent dispatch remains templated/pseudocode ('Task: Research {unknown}...') rather than fully copy-paste ready.	4 / 5
Workflow Clarity	Steps are clearly sequenced with per-phase prerequisites and outputs plus validation checkpoints (gate evaluation, Constitution Check re-evaluation), but the error path is only 'ERROR' without an explicit fix-and-retry feedback loop.	4 / 5
Progressive Disclosure	No bundle files exist and the single-file content is well organized into clear sections (User Input, Pre-Execution Checks, Outline, Phases, Key rules); the duplicated hook block is the main organization gap keeping it just below 5.	4 / 5
	Total	16 / 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 clearly states the skill's purpose and sits in a distinct niche, but it omits any 'Use when...' trigger guidance and relies on technical jargon rather than natural user phrases. Specificity is adequate but the named actions remain somewhat abstract.

Suggestions

Add an explicit 'Use when...' clause naming natural trigger phrases such as 'planning a feature implementation', 'creating an implementation plan', or 'designing spec-kit artifacts'.

Replace the generic 'generate design artifacts' with concrete outputs the user would recognize (e.g. 'produce research.md, data-model.md, and contract files').

Include user-facing synonyms or file/keyword cues (e.g. 'implementation plan', 'spec-kit', 'design phase') to improve trigger term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('implementation planning') and a couple of actions ('execute the implementation planning workflow', 'generate design artifacts'), but the actions are abstract and 'design artifacts' is generic rather than concrete.	3 / 5
Completeness	It gives a clear 'what' (execute the planning workflow, generate design artifacts) but provides no 'when' guidance at all, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	There is no 'Use when...' clause and the terms present ('plan template', 'design artifacts') are technical jargon; only 'implementation planning' is a mildly natural keyword, so the natural phrases users would say are missing.	2 / 5
Distinctiveness Conflict Risk	It targets a specific niche (spec-kit implementation planning) with low conflict risk, though the absence of an explicit distinct trigger phrase keeps it just below a 5.	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: unoplatform/uno
Path: .claude/skills/speckit-plan/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.