CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

openspec-bulk-archive-change

Archive multiple completed changes at once. Use when archiving several parallel changes.

56

Quality

70%

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-bulk-archive-change/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 strong, highly actionable body with a clear sequenced workflow, explicit validation and confirmation checkpoints, and good failure handling for a destructive batch operation. Its weaknesses are redundancy across the four overlapping output templates and the absence of any progressive disclosure — everything, including lengthy examples, lives inline in SKILL.md.

Suggestions

Collapse step 9's example summary and the three "Output On ..." template sections into one canonical output section — the current duplication costs dozens of lines without adding information.

Move the Conflict Resolution Examples and output templates to a references/ file (e.g., references/conflict-examples.md) linked from the body, shortening SKILL.md to the workflow itself.

Replace the deferred "openspec-sync-specs approach" reference and the unspecified creation-date source with concrete steps (e.g., how to read change creation dates for chronological ordering) so every action is self-contained.

DimensionReasoningScore

Conciseness

Mostly efficient with no explanation of concepts Claude already knows, but noticeably redundant: step 9's example summary duplicates the "Output On Success" and "Output On Partial Success" templates almost verbatim, and the Guardrails section re-states rules already given inline (e.g., "Always prompt for selection, never auto-select" repeats step 2's IMPORTANT). Not score 4 because the output-template duplication is a clear trim candidate; not score 2 because there is no padding or tutoring of known concepts.

3 / 5

Actionability

Concrete, executable guidance throughout: `openspec list --json`, `openspec status --change "<name>" --json`, task-counting via `- [ ]`/`- [x]`, requirement extraction pattern `### Requirement: <name>`, and copy-paste `mkdir -p`/`mv` archive commands. Not score 5 because step 8a defers spec sync to an unspecified "openspec-sync-specs approach" and chronological ordering depends on change creation dates without any command for obtaining them; not score 3 because nearly all steps are directly executable.

4 / 5

Workflow Clarity

The batch/destructive operation is well served: a 9-step sequence with pre-flight validation (step 3), conflict detection (step 4), a consolidated status table before a single user confirmation (steps 6-7), per-change outcome tracking (success/skip/fail), and explicit failure isolation ("If archive target exists, fail that change but continue with others"). Not score 5 because there is no post-archive verification or validate-and-retry feedback loop (e.g., re-running `openspec list` to confirm, or validating spec sync results); not score 3 because validation checkpoints are explicitly present, so the batch-operation cap does not apply.

4 / 5

Progressive Disclosure

Sections are well labeled (Steps, Conflict Resolution Examples, Output templates, Guardrails) but the ~235-line body is fully inline with no references/ bundle: the conflict-resolution examples and the three output template sections are content that would fit naturally in one-level-deep reference files. Not score 2 because structure is clear and navigation within the file is easy; not score 4 because no content is split out despite the length exceeding what the body alone should carry.

3 / 5

Total

14

/

20

Passed

Description

62%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 concise, in third person, and correctly structured with both a what and a Use-when clause. It is thin on capability detail and trigger variations, relying on one narrow trigger phrase ("several parallel changes") that users may not naturally say.

Suggestions

Expand the what-clause with 2-3 concrete capabilities, e.g., "Validates artifact and task completion, detects and resolves spec conflicts, and syncs delta specs" — this would raise specificity.

Broaden the when-clause with natural trigger variations users would actually say: "Use when bulk archiving, batch archiving, or archiving all completed openspec changes".

Anchor the description to the openspec context (e.g., mention openspec changes) to reduce overlap with generic archive/cleanup skills.

DimensionReasoningScore

Specificity

"Archive multiple completed changes at once" names the domain (archiving completed changes) and exactly one concrete action (batch archive). Not score 4 because it does not list several specific actions (e.g., conflict detection, spec syncing, validation); not score 2 because the action named is concrete rather than generic.

3 / 5

Completeness

Both parts are present: "Archive multiple completed changes at once" (what) and "Use when archiving several parallel changes" (when). Not score 5 because the 'when' clause offers only a single narrow trigger phrase without variations or synonyms (contrast the anchor-5 example listing multiple concrete triggers); not score 3 because the 'when' is explicit, not merely implied.

4 / 5

Trigger Term Quality

Relevant keywords exist ("archive", "changes", "several parallel changes") but common variations users would naturally say — "bulk archive", "batch archive", "archive all completed changes", "openspec cleanup" — are missing, and "several parallel changes" is an uncommon phrasing. Not score 4 because keyword coverage is thin, not score 2 because the terms present are on-topic rather than generic.

3 / 5

Distinctiveness Conflict Risk

The plural framing ("multiple completed changes at once") distinguishes it from a single-change archive skill, and the trigger clause narrows it further. Not score 5 because it does not mention the openspec context, leaving minor overlap risk with any other change-archiving or cleanup skill; not score 3 because the bulk/plural framing is genuinely distinguishing.

4 / 5

Total

14

/

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

dwmkerr/git-workforest

Path

.claude/skills/openspec-bulk-archive-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.