CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openspec-propose

Propose a new OpenSpec change with all artifacts generated in one step. Use when the user wants to quickly describe what they want to build and get a complete proposal with design, specs, and tasks ready for implementation. Also use when the user says "openspec propose" or "opsx propose".

Quality

87%

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

SKILL.md
Quality
Evals
Security

Quality

Content

81%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.

A highly actionable, well-sequenced workflow skill: every step has concrete commands, explicit validation checkpoints, and error-recovery branches. Its main cost is token weight — the store-flag and planning-boundary rules are repeated across sections, and the ~163-line single file inlines edge-case handling that could live in reference files.

Suggestions

State the --store stickiness rule once (in the Store selection section) and refer back to it from steps 2-4 instead of re-explaining flag appending each time.

Consolidate the planning-boundary rule: keep it in the opening Planning boundary section and drop the restatements in step 2 and Guardrails, or shorten those to one-line reminders.

Move the extended root-null / store-declaration error handling (the 'Declared in' / 'Invalid store declaration' branch and the auto-selected vs explicit-request branches) into a reference file linked from a short Project check section.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but redundancy is more than minor: the --store stickiness rule is restated in the Store selection section and again in steps 2, 3, and 4; the planning boundary is stated three times (opening, step 2, Guardrails); and root-null handling is explained in both Project check and step 2. This matches 'mostly efficient but could be tightened' rather than the 4 anchor's 'minor instances'.

3 / 5

Actionability

Fully executable, copy-paste-ready commands throughout ('openspec new change "<name>"', 'openspec status --change "<name>" --json', 'openspec instructions <artifact-id> --change "<name>" --json'), with named JSON fields to parse (applyRequires, artifacts, resolvedOutputPath) and concrete artifact filenames. Matches the 5 anchor for an instruction-only skill with specific, complete guidance.

5 / 5

Workflow Clarity

Clear numbered sequence (steps 1-7) with explicit validation checkpoints: confirm root before any write, re-run status after each artifact, verify each artifact file exists before proceeding, and error-recovery branches (root:null handling, instruction-delegation fallback, 'stop and tell the user'). A todo-list checklist is specified. Matches the 5 anchor's explicit validation plus feedback loops; the 4 anchor's 'minor validation gaps' does not apply.

5 / 5

Progressive Disclosure

No bundle files exist, and the body is well-organized with clear section headers (Planning boundary, Store selection, Project check, Steps, Output, Artifact Creation Guidelines, Guardrails). Not 5 because at ~163 lines the store/root edge-case handling is inline content that could be split into a referenced file, and there are no well-signaled references; not 3 because structure and placement are good, not merely present.

4 / 5

Total

17

/

20

Passed

Description

87%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.

A strong description: it states concrete capabilities with enumerated artifact types, gives an explicit 'Use when...' clause with literal command triggers, and occupies a distinct niche. The only weakness is modest trigger synonym coverage beyond the two command invocations.

DimensionReasoningScore

Specificity

Names the domain (OpenSpec change proposals) and several concrete actions — 'Propose a new OpenSpec change with all artifacts generated in one step' with 'a complete proposal with design, specs, and tasks'. Not 5 because coverage has minor gaps (e.g., no mention of status checks or artifact scaffolding); not 3 because it lists more than 1-2 actions with concrete artifact types.

4 / 5

Completeness

Explicitly answers both: what ('Propose a new OpenSpec change with all artifacts generated in one step... complete proposal with design, specs, and tasks') and when ('Use when the user wants to... Also use when the user says "openspec propose" or "opsx propose"') with concrete trigger phrases. Clear match to the 5 anchor; the 4 anchor applies only when the 'when' is less explicit.

5 / 5

Trigger Term Quality

Includes explicit natural triggers users would say: 'openspec propose' and 'opsx propose', plus a paraphrased trigger ('when the user wants to quickly describe what they want to build'). Not 5 because common variations like 'create a change', 'plan a change', or 'new openspec change' are missing; not 3 because coverage goes beyond 'some relevant keywords'.

4 / 5

Distinctiveness Conflict Risk

Clear niche (OpenSpec change proposals) with distinct command-style triggers ('openspec propose', 'opsx propose') that no other skill would claim. Only negligible overlap risk with the sibling apply workflow referenced in the body; matches the 'clear niche with distinct triggers' anchor.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Fission-AI/OpenSpec

Path

skills/openspec-propose/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.