CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openspec-continue-change

Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

Quality

78%

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 ./.claude/skills/openspec-continue-change/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 lean, executable workflow: every CLI call is concrete with flags, JSON output fields are enumerated, branching logic covers all status outcomes, and guardrails enforce one-artifact-per-invocation discipline. The only notable weaknesses are mild duplication of the context/rules guidance, a verification step that lives in guardrails rather than the step flow, and schema-specific patterns inlined that could be a reference file.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence: it jumps straight into commands and JSON fields with no concept explanations or padding ('Run `openspec list --json` to get available changes sorted by most recently modified'). Minor repetition could be trimmed — the context/rules-as-constraints point appears both in the field list ('constraints for you - do NOT include in output') and again as a bolded Guardrails item, and 'STOP after creating ONE artifact' duplicates 'Create ONE artifact per invocation'.

4 / 5

Actionability

Concrete, copy-paste-ready commands with flags are given (`openspec list --json`, `openspec status --change "<name>" --json`, `openspec instructions <artifact-id> --change "<name>" --json`) plus an enumerated list of parsed JSON fields and concrete selection-display criteria. It falls short of the fully-executable anchor only because the artifact-writing step is delegated to runtime CLI output ('Use `template` as the structure - fill in its sections') with no sample artifact content — a justified flexibility, but still a gap versus specific examples covering common cases.

4 / 5

Workflow Clarity

Steps 1-4 are clearly numbered and sequenced with explicit branching on status ('If all artifacts are complete', 'If artifacts are ready to create', 'If no artifacts are ready (all blocked)') and an explicit STOP after one artifact. A verification checkpoint exists ('Verify the artifact file exists after writing before marking progress'), but it sits in the Guardrails section rather than the step sequence and has no retry/fix loop, fitting 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

The single-file body is well organized with clear sections (**Input**, **Steps**, **Output**, **Artifact Creation Guidelines**, **Guardrails**) and horizontal rules separating status branches; no bundle files exist and none are referenced. Minor organization gap: the schema-specific artifact patterns (spec-driven and tdd walkthroughs) are inline reference-style content that could live in a separate file, keeping it at 'good structure; most content appropriately placed' rather than the fully-split 5 anchor.

4 / 5

Total

16

/

20

Passed

Description

70%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 well-formed with an explicit 'Use when' clause, third-person voice, and a specific, named domain. Its main weakness is thin capability coverage: it names only 'creating the next artifact' and its trigger clause largely mirrors the what-statement instead of adding varied natural trigger phrases.

Suggestions

Enumerate the concrete artifact types the skill can produce (e.g., 'create the next artifact — proposal, specs, design, or tasks — and check change status') to raise specificity.

Diversify the trigger clause with natural user phrasings like 'keep going', 'pick up where I left off', or 'what's next on this change' instead of restating the capability.

Add a distinguishing cue such as 'requires the openspec CLI' or 'for in-progress changes' to further separate it from sibling OpenSpec workflow skills.

DimensionReasoningScore

Specificity

The description names the domain ('an OpenSpec change') and one concrete action ('creating the next artifact'), matching the anchor for naming a domain with 1-2 concrete actions but not comprehensive coverage. It omits other concrete capabilities visible in the body (checking status via `openspec status`, creating proposal/specs/design/tasks artifacts), so it does not reach the 'several specific actions' anchor.

3 / 5

Completeness

Both parts are explicitly present: the 'what' is 'Continue working on an OpenSpec change by creating the next artifact' and the 'when' is 'Use when the user wants to progress their change...'. However, the 'when' clause largely restates the 'what' rather than adding distinct concrete trigger phrases, fitting the anchor where 'when' could be more explicit or specific rather than the fully concrete 5 anchor.

4 / 5

Trigger Term Quality

The trigger phrases 'progress their change', 'create the next artifact', and 'continue their workflow' give good coverage of the natural continue-family phrasings a user would say. A few common variations are missing (e.g., 'keep going', 'next step', 'pick up where I left off', 'finish the change'), so it stops short of the comprehensive-synonyms anchor.

4 / 5

Distinctiveness Conflict Risk

The 'OpenSpec change' niche is specific and product-named, giving a clear distinct identity with minimal generic conflict. Minor overlap risk remains with sibling OpenSpec workflow skills (e.g., starting or archiving a change) since 'continue their workflow' is a broad phrasing, so it fits 'mostly distinct; minor overlap risk with closely related skills' rather than the minimal-conflict 5 anchor.

4 / 5

Total

15

/

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

PBH-BTN/PeerBanHelper

Path

.claude/skills/openspec-continue-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.