CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openspec-update-change

Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Also use when the user says "openspec update change" or "opsx update". If the user means the openspec update CLI command, which refreshes generated files, run that command instead. Never edits code.

Quality

95%

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

88%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 tightly written operational workflow with exact commands, JSON fields to parse, and strong validation/confirmation checkpoints throughout. Its only weaknesses are minor: a few repeated statements (never-edit-code, write-ownership) and a dense preamble that inflates token usage without bundle-file offloading.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious operational detail (store stickiness, `root: null` handling, glob artifact rules) and assumes Claude's competence — no basic concepts are explained. However, there is minor redundancy that could be trimmed: "Never edit code" appears in the opening line and again in Guardrails, step 4's "step 5 owns every write" is restated in step 5 ("This step performs every artifact write in this workflow"), and the store-selection paragraph re-explains the flag-append rule twice. This fits the 4 anchor (efficient with minor over-explanation), not 5, since a few sentences genuinely repeat.

4 / 5

Actionability

Guidance is fully executable throughout: exact commands (`openspec status --change "<name>" --json`, `openspec instructions "<artifact-id>" --change "<name>" --json`, `openspec list --json`) with the specific JSON fields to read (`root`, `existingOutputPaths`, `isPlanningComplete`), concrete error-message prefixes to branch on ("Declared in", "Invalid store declaration in"), exact user-facing output requirements, and specific filesystem checks ("a create operation that fails if the target already exists"). This is an instruction-only skill and its guidance is copy-paste actionable, matching the top anchor.

5 / 5

Workflow Clarity

Six clearly sequenced steps with explicit validation checkpoints and feedback loops: the project check reads `root` before any write and interprets a non-zero exit as an answer rather than a failure; glob-file creation re-checks scope/skip status and concrete-path containment immediately before writing; every edit is confirmed with the user before being applied; and failure branches say to stop and reconcile rather than overwrite. This matches the anchor requiring explicit validation steps and error-recovery loops.

5 / 5

Progressive Disclosure

There are no bundle files, and the body is well organized with clearly signaled sections (Store selection, Project check, Input, Steps, Output, Guardrails) and no nested references. This fits the 4 anchor (good structure, minor organization gaps) rather than 5 because the >50-line simple-skill exception doesn't apply and the long store-selection/project-check preamble is dense inline material that could plausibly live in a shared reference; it is not 3 because the content is procedural workflow that must be followed linearly, not bulk reference material wrongly inlined.

4 / 5

Total

18

/

20

Passed

Description

100%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 is exemplary: concrete third-person actions, explicit use-when triggers with synonyms and literal invocation phrases, and explicit disambiguation against the similarly-named CLI command. Both the what and the when are answered clearly with no fluff.

DimensionReasoningScore

Specificity

The description lists multiple concrete actions — "revising its existing planning artifacts", "keeping them coherent with one another", "fold new decisions into it", "reconcile its artifacts after an edit" — plus an explicit scope constraint ("Never edits code"). This matches the anchor for multiple specific concrete actions with comprehensive coverage; it is not the 4 anchor because there are no noticeable coverage gaps for this skill's domain.

5 / 5

Completeness

It explicitly answers both questions: what ("Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent") and when ("Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit"). It even adds a disambiguation clause for the CLI command; this clearly matches the top anchor with concrete trigger phrases.

5 / 5

Trigger Term Quality

It covers natural trigger phrases comprehensively: "revise a change's plan", "fold new decisions into it", "reconcile its artifacts after an edit", and the literal invocations "openspec update change" and "opsx update". Synonym variations (revise/update/fold in/reconcile) are all present; it is above the 4 anchor because no commonly used phrasing for this intent is missing.

5 / 5

Distinctiveness Conflict Risk

It carves out a clear niche (revising existing OpenSpec change artifacts) and actively reduces conflict risk by redirecting the CLI-command interpretation ("If the user means the openspec update CLI command... run that command instead") and scoping to planning artifacts only. Minimal overlap risk with sibling skills; matches the clear-niche anchor.

5 / 5

Total

20

/

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-update-change/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.