CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

speckit-constitution

Create or update the project constitution from interactive or provided principle inputs.

Quality

68%

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 ./apps/reference/.claude/skills/speckit-constitution/SKILL.md

The canonical home for this skill is speckit-constitution in RihardsJ/software-factory

SKILL.md
Quality
Evals
Security

Quality

Content

70%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 strong procedural skill: an unambiguous numbered workflow with concrete commands, explicit validation, error recovery, and careful safeguards around the constitution overwrite. Its two real weaknesses are the near-verbatim duplication of the extension-hook protocol across pre- and post-execution sections (hurting both conciseness and organization) and the absence of any bundle files to offload that shared protocol. Tightening the duplicated blocks into a single section or a references/hooks.md file would address both at once.

Suggestions

Factor the duplicated pre/post extension-hook protocol into a single shared section (or a references/hooks.md file) parameterized by the hook key (before_constitution vs after_constitution) — this removes ~30 lines of verbatim repetition and improves both conciseness and progressive disclosure.

Trim the verbose hook-error sentence ('do not skip silently: tell the user that ... and that no hooks were checked, including any mandatory (optional: false) hooks registered there, then continue normally') to one crisp instruction since it currently appears twice.

Include one short example of a resolved constitution skeleton (headings plus one placeholder-filled principle) so step 3's drafting guidance is fully copy-paste concrete.

DimensionReasoningScore

Conciseness

The body is dense procedural content with no explanations of concepts Claude already knows, but the entire ~30-line extension-hook protocol appears twice nearly verbatim (Pre-Execution and Post-Execution Checks), and long sentences such as the 'do not skip silently: tell the user that .specify/extensions.yml could not be read...' instruction repeat word-for-word. Mostly efficient but could be tightened by factoring the duplicated hook protocol into one section, fitting the anchor for some unnecessary explanation; not score 2 because the padding is one concentrated duplication pattern rather than several scattered padded sections.

3 / 5

Actionability

Concrete, executable guidance throughout: 'Run .specify/scripts/bash/resolve-template.sh constitution-template --json' and parse TEMPLATE_CONTENT, placeholder token form '[ALL_CAPS_IDENTIFIER]', 'TODO(<FIELD_NAME>): explanation', explicit MAJOR/MINOR/PATCH bump rules, ISO date format, and exact hook output blocks. Minor gaps: no example of the resolved template structure and the hook invocation mechanism is described abstractly ('the invocation may differ from the literal {command} id'), so it fits 'mostly executable guidance with minor gaps' rather than the fully copy-paste-ready anchor.

4 / 5

Workflow Clarity

A clear 7-step numbered sequence with an explicit validation checklist (step 5: no unexplained bracket tokens, version line matches report, ISO dates), error recovery ('If it fails, stop and report the resolution error; do not continue'), clarification loops ('If it is unclear whether an instruction is constitution content, ask for clarification before making changes'), and safeguards around the destructive overwrite (preserve still-applicable values, Sync Impact Report). Matches the anchor for clear sequence with explicit validation steps, feedback loops for error recovery, and checklists.

5 / 5

Progressive Disclosure

No bundle files exist, so all content is inlined in a ~170-line body — well over the under-50-line exception for single-file skills. Section structure is clear (Scope Guard, Pre/Post-Execution Checks, numbered Outline), but the duplicated pre/post hook protocol (~60 lines combined) is content that clearly belongs in a shared reference file. Fits 'some structure but could be better organized; content that should be separate is inline'; not score 4 because the duplication is a real organization gap, not a minor one.

3 / 5

Total

15

/

20

Passed

Description

53%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 but provides no "when to use" trigger guidance, which caps both completeness and trigger-term quality at the midpoint. It is distinct within the spec-kit domain yet could be confused with adjacent spec-kit governance commands. A single added sentence with natural trigger phrases would lift three of the four dimensions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when the user wants to create, amend, or ratify the project constitution, add or revise principles, or asks about project governance values.'

Include natural trigger synonyms users would actually say: 'constitution', 'principles', 'values', 'governance', 'amend', 'ratify'.

Briefly enumerate the concrete actions involved (resolve the constitution template, fill in principles, bump the version, write the sync impact report) to raise specificity from 1-2 actions to several.

DimensionReasoningScore

Specificity

"Create or update the project constitution" names the domain plus two concrete actions, but stops there without covering what the update involves (versioning, principles, governance sections). This matches the anchor for naming a domain with 1-2 concrete actions that is not comprehensive; it is not score 4 because it does not list several specific actions.

3 / 5

Completeness

The "what" is clear (create or update the project constitution) but there is no "when"/"Use when" clause anywhere, which caps completeness at 3 per the judging guidelines. Exactly matches the anchor for a clear "what" with "when" missing; not score 4, which requires both to be present.

3 / 5

Trigger Term Quality

"constitution" and "principle inputs" are relevant keywords, but common variations users would naturally say ("governance", "values", "amend the constitution") are missing, and "interactive or provided principle inputs" is stilted phrasing rather than natural trigger language. Fits the anchor for some relevant keywords but missing common variations or synonyms.

3 / 5

Distinctiveness Conflict Risk

"Project constitution" is a clear niche that is unlikely to trigger for unrelated skills, but the absence of explicit trigger guidance and proximity to related spec-kit commands (e.g., /speckit-specify) leaves minor overlap risk. Fits "mostly distinct; minor overlap risk with closely related skills"; not score 5, which expects distinct triggers the description does not supply.

4 / 5

Total

13

/

20

Passed

Validation

87%

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

CriteriaDescriptionResult

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

RihardsJ/software-factory

Path

apps/reference/.claude/skills/speckit-constitution/SKILL.md

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.