CtrlK
BlogDocsLog inGet started
Tessl Logo

speckit-plan

Generate technical implementation plans from feature specifications. Use after creating a spec to define architecture, tech stack, and implementation phases. Creates plan.md with detailed technical design.

60

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./bundled/skills/speckit-plan/SKILL.md
SKILL.md
Quality
Evals
Security

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 a well-sequenced, actionable planning workflow with explicit checkpoints and concrete commands. Its main limitation is error handling expressed as stop-on-ERROR rather than validate-fix-retry feedback loops.

Suggestions

Replace bare "ERROR on gate failures" with an explicit feedback loop: report the violation, attempt a fix, then re-evaluate the gate before proceeding, to reach anchor 5 workflow clarity.

Convert the research-dispatch pseudocode block into concrete dispatched-task instructions or an executable template so the actionability is fully copy-paste ready.

Tighten minor asides (e.g. "These scripts detect which AI agent is in use. Update the appropriate agent-specific context file.") into a single concise line to improve conciseness.

DimensionReasoningScore

Conciseness

The body is largely lean — numbered outline, phase steps, and a short key-rules section — with only minor explanatory asides ("These scripts detect which AI agent is in use") that could be trimmed, fitting the efficient-but-slightly-trimmable anchor 4.

4 / 5

Actionability

Concrete commands (setup-plan.ps1 -Json, update-agent-context.ps1 -AgentType codex), named output files, and a Decision/Rationale/Alternatives format give mostly executable guidance, with the research-dispatch block remaining template-like rather than fully executable.

4 / 5

Workflow Clarity

A clear Setup → Load context → Execute → Stop sequence with prerequisites ("research.md complete") and checkpoints (gate evaluation, Constitution Check, re-evaluation post-design) is present; validation is mostly stop-on-error rather than an explicit fix-and-retry loop, leaving a minor gap below anchor 5.

4 / 5

Progressive Disclosure

Content is well-organized into Outline, Phases, and Key rules with one-level references to project files (constitution.md, IMPL_PLAN, contracts/); no bundle files exist to offload detail into, so the single-file structure is appropriate with only minor organization gaps.

4 / 5

Total

16

/

20

Passed

Description

67%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 what the skill does and when to use it with several concrete actions and a distinct spec-planning niche. It is held back by trigger phrasing tied to workflow position rather than natural user requests and limited synonym coverage.

Suggestions

Add a natural-language trigger clause such as "Use when the user asks to plan a feature's implementation or design its architecture after a spec exists" to strengthen trigger_term_quality and completeness.

Include user-facing synonyms (e.g. "technical design", "implementation plan", "feature plan") alongside "spec" to broaden keyword coverage.

Mention the spec-kit context in the description itself (not only compatibility) to further reduce overlap with generic planning skills.

DimensionReasoningScore

Specificity

Lists several concrete actions — "Generate technical implementation plans", "define architecture, tech stack, and implementation phases", "Creates plan.md" — with only minor abstraction in the verbs, falling short of the fully comprehensive anchor 5.

4 / 5

Completeness

Both what ("Generate technical implementation plans... Creates plan.md") and when ("Use after creating a spec") are present, but the when is a workflow-position trigger rather than an explicit user-request phrase, fitting the anchor 4 example.

4 / 5

Trigger Term Quality

Relevant terms ("spec", "implementation plans", "plan.md", "architecture", "tech stack") appear but common natural variations a user would say (e.g. "plan a feature", "technical design") are missing, matching the some-keywords-but-missing-synonyms anchor.

3 / 5

Distinctiveness Conflict Risk

The spec-driven planning niche ("implementation plans from feature specifications", "Creates plan.md") is mostly distinct with only minor overlap risk against general planning skills, matching the mostly-distinct anchor 4.

4 / 5

Total

15

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository
foryourhealth111-pixel/Vibe-Skills
Reviewed

Table of Contents

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.