CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openspec-sync-specs

Sync delta specs from an OpenSpec change to main specs. Use when the user wants to update main specs with changes from a delta spec, without archiving the change. Also use when the user says "openspec sync" or "opsx sync".

Quality

83%

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

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 highly actionable, well-sequenced workflow with concrete commands, JSON contracts, format references, and strong safety guardrails around destructive operations. Its main costs are redundancy between the step sections and the Guardrails section, and the lack of a fix-and-revalidate loop after the final validation step.

Suggestions

Deduplicate the Guardrails section: drop the four bullets that restate step 3/4 rules verbatim (artifactPaths-only, caller-supplied subset, fetch-once/reuse-snapshot, stop-on-invalid-instructions) or compress each to a one-line pointer, and state 'Never write an empty ## Requirements section' only once.

Break the store-selection paragraph into a short bullet list (discover ids, append --store to the listed commands, keep it sticky) so the dense prose block is scannable.

In step 5, add a fix-and-revalidate loop: on validation failure, fix the merged main spec and re-run `openspec validate --specs` before reporting, reserving report-and-stop for failures that persist.

DimensionReasoningScore

Conciseness

The body assumes OpenSpec knowledge and avoids concept explanations, but is repetitive: the Guardrails section restates step 3/4 rules nearly verbatim (artifactPaths-only, caller-supplied subset, fetch-once, stop-on-invalid), "Never write an empty `## Requirements` section" appears twice, and the store-selection paragraph is a dense single-block wall. This fits 'mostly efficient but could be tightened' rather than the noticeably padded anchor 2, since the redundancy is restatement of real rules, not filler.

3 / 5

Actionability

Fully executable instruction-only guidance: copy-paste-ready commands ("openspec status --change \"<name>\" --json", "openspec validate --specs"), concrete JSON contracts to read (planningHome.root, artifactPaths.specs.existingOutputPaths, rules), exact file paths, complete delta/main spec format references, and a ready output summary template.

5 / 5

Workflow Clarity

A clear 6-step sequence with a pre-write checkpoint (instructions snapshot, "stop before every main-spec write" on non-zero/invalid JSON) and a post-write `openspec validate --specs` checkpoint with explicit failure handling, plus extensive safety conditions on the destructive spec-deletion path. It falls short of anchor 5 only because a validation failure instructs report-and-stop with no fix-and-revalidate loop.

4 / 5

Progressive Disclosure

A single-file skill (no bundle directories exist) that is well-sectioned with clear headers and no nested-reference or navigation problems, and the inlined format references are needed on every run; however, the ~280-line body keeps stable reference material (format examples, output template) inline where a split could shrink the always-loaded payload, matching 'good structure; minor organization gaps' rather than the well-split anchor 5.

4 / 5

Total

16

/

20

Passed

Description

82%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 cleanly and explicitly states both what the skill does and when to use it, with natural-language plus command-form triggers including a synonym. Its only limitation is that it names a single action (sync) rather than listing several concrete capabilities.

DimensionReasoningScore

Specificity

"Sync delta specs from an OpenSpec change to main specs" names the domain concretely with a single clear action (sync), but does not enumerate several distinct capabilities, matching the '1-2 concrete actions, not comprehensive' anchor rather than the 'several specific actions' anchor above.

3 / 5

Completeness

Explicitly answers both: what ("Sync delta specs from an OpenSpec change to main specs") and when ("Use when the user wants to update main specs with changes from a delta spec... Also use when the user says 'openspec sync' or 'opsx sync'") with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Includes natural phrases ("update main specs with changes from a delta spec", "without archiving the change") plus both command forms ("openspec sync" and the synonym "opsx sync"), giving good coverage; a few natural variants users might say (e.g., "apply delta specs", "merge specs") are missing, so it is not the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

A clear niche (OpenSpec delta-spec syncing) with distinct command-style triggers, and the qualifier "without archiving the change" explicitly separates it from a sibling archive skill, so conflict risk is minimal.

5 / 5

Total

17

/

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-sync-specs/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.