CtrlK
BlogDocsLog inGet started
Tessl Logo

openspec-archive-change

Archive a completed OpenSpec change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete. Also use when the user says "openspec archive" or "opsx archive".

66

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 ./skills/openspec-archive-change/SKILL.md
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.

A rigorous, highly actionable workflow with excellent sequencing, validation checkpoints, and failure recovery for a destructive archive operation. Its weaknesses are token efficiency — repeated contracts and a Guardrails section that restates the steps — and a monolithic single-file layout with an unlinked dependency on the openspec-sync-specs skill.

Suggestions

Trim the instructions-archive context/operationGuidance block and the Guardrails section to rules not already stated in the steps; lines like "Never archive while a spec sync is still in flight" and "If delta specs exist, always run the sync assessment" duplicate step 4 verbatim.

Replace step 4's nested conditional prose (ADDED/MODIFIED/REMOVED/RENAMEED combinations) with a compact delta-composition-to-outcome table to cut tokens and speed parsing.

Move the shared store-selection/project-check preamble into a referenced file (e.g. references/store-selection.md) and give the `openspec-sync-specs` workflow a concrete path or link so the inline-sync call is actionable.

DimensionReasoningScore

Conciseness

The body is information-dense with no conceptual padding (it never explains what OpenSpec is), but the instructions-archive context/operationGuidance block restates the same contract several ways ("Keep both fields separate from built-in steps...", "Do not infer replacement paths...", "These are prompt-level behavior contracts, not enforceable checks"), the Guardrails section repeats rules already stated in steps 3-5, and step 4's nested conditional prose could be a compact table. It could be noticeably tightened without losing anything.

3 / 5

Actionability

Nearly every step has copy-paste commands with exact JSON fields to read ("openspec status --change \"<name>\" --json", "mkdir -p \"<planningHome.changesDir>/archive\"", "mv \"<changeRoot>\"...") plus exact prompt options and an output template. The gap: step 4 says "run the `openspec-sync-specs` workflow inline" with no concrete invocation or reference, and the post-sync verification ("re-run the comparison from the top of this step") prescribes checks without a method for performing them.

4 / 5

Workflow Clarity

Six clearly sequenced numbered steps with explicit validation checkpoints and feedback loops throughout: strict JSON parsing rules ("Require exactly one match and nonnegative integer totalTasks"), confirm-before-proceed warnings, sync-blocked logic, post-sync re-verification ("re-run the comparison from the top of this step... each capability must now read as already synced"), and stop-on-failure handling ("report what differs and stop — do not archive"), plus a Guardrails checklist. This matches the top anchor for a destructive move workflow.

5 / 5

Progressive Disclosure

The single ~220-line file is well-sectioned but everything lives inline: the generic store-selection and project-check preamble reads like shared boilerplate, and step 4's canonical sync contract is reference-shaped content that could sit in a separate file. The one external dependency it names ("run the `openspec-sync-specs` workflow inline") is not signaled with a path or link, so navigation to it is implicit.

3 / 5

Total

15

/

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 tight, well-formed description: it states a concrete single-purpose action in a specific domain, gives explicit 'Use when' triggers including the exact slash-command phrasings a user would say, and stays in third-person voice. Its only weakness is that it undersells the skill's full scope (verification and delta-spec sync are unmentioned).

DimensionReasoningScore

Specificity

"Archive a completed OpenSpec change in the experimental workflow" and "finalize and archive a change" name concrete, specific actions in a well-defined domain with a clear workflow context. Falls short of the 5 anchor because the spec-sync and verification work the skill actually performs is not mentioned, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both what ("Archive a completed OpenSpec change in the experimental workflow") and when ("Use when the user wants to finalize and archive a change after implementation is complete. Also use when the user says "openspec archive" or "opsx archive"") with concrete trigger phrases, matching the top anchor exactly.

5 / 5

Trigger Term Quality

Includes natural user phrasings: "openspec archive", "opsx archive", "finalize and archive a change", and "after implementation is complete". A few natural synonyms are missing (e.g. "done with a change", "close out the change"), so it matches the good-coverage anchor rather than the comprehensive one.

4 / 5

Distinctiveness Conflict Risk

The OpenSpec-specific triggers ("openspec archive", "opsx archive", "OpenSpec change") carve out a clear niche with distinct trigger phrases; conflict risk with other skills is minimal.

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
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.