workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still an open loop, and what was just started. Use when someone asks "what happened this week", "what is still open", "what did the team finish", "give me the weekly rollup", or wants a status report over a .specstory/history corpus.

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

100%

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, well-sequenced workflow that delegates the heavy lifting to a clearly signaled engine and keeps only synthesis/orchestration inline. It meets the top anchor on all four dimensions, with only a minor tightening opportunity in the opening framing.

Dimension	Reasoning	Score
Conciseness	The ~50-line body is lean and purposeful: it explains only engine-specific concepts Claude would not know (lifecycle statuses, deterministic output) and avoids teaching known concepts. A two-sentence orientation restates the description mildly, but every section earns its place, matching the top rather than the mostly-efficient level 2 anchor.	3 / 3
Actionability	Provides fully executable commands, e.g. `node "${CLAUDE_SKILL_DIR}/scripts/workthreads.mjs" threads --db <db> --days 7 --json`, with flag variants (--scan/--dir/--out) and a concrete 5-part rollup shape plus a dated output path. Copy-paste ready and specific, matching the top anchor rather than the pseudocode/incomplete level 2.	3 / 3
Workflow Clarity	A clear numbered sequence (index -> threads -> write rollup -> save to dated file) with explicit sub-steps (a-e), an evidence-citation checkability step ('cite evidence refs (path:line) so each claim is checkable'), and a week-in-progress caveat. The deterministic read-only engine removes the need for a retry loop, so this meets the top anchor and is not capped at 2 (no destructive/batch op).	3 / 3
Progressive Disclosure	SKILL.md is an overview that delegates retrieval/clustering/classification to the real one-level-deep engine at scripts/workthreads.mjs (verified present) and keeps synthesis guidance inline. Content is appropriately split into well-organized sections with no nested references, matching the top anchor rather than the monolithic or under-signaled level 2.	3 / 3
	Total	12 / 12 Passed

Description

100%

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 third person, concrete, and explicitly pairs capabilities with natural 'Use when' triggers tied to a distinct .specstory/history niche. It hits the top anchor on every dimension.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions: 'groups the window's sessions into threads of work per project', 'labels each new / open / recently closed', and produces a 'weekly work-thread rollup'. This matches the top anchor (multiple specific concrete actions), not level 2 (which only names a domain plus partial actions).	3 / 3
Completeness	Explicitly answers both what (rollup that groups sessions into threads and labels lifecycle status) and when ("Use when someone asks..."). The explicit 'Use when' clause places it at the top anchor; it is not level 2 because the trigger is stated, not merely implied.	3 / 3
Trigger Term Quality	Quotes natural phrases a user would actually say: "what happened this week", "what is still open", "what did the team finish", "give me the weekly rollup", and "status report". Good coverage of natural variations, matching the top anchor rather than the partial-coverage level 2.	3 / 3
Distinctiveness Conflict Risk	Occupies a clear niche (SpecStory coding histories over a .specstory/history corpus, weekly team rollup) with triggers tied to that corpus, making conflict with other skills unlikely. This is the top anchor, not the somewhat-overlapping level 2.	3 / 3
	Total	12 / 12 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: specstoryai/getspecstory
Path: workthreads/SKILL.md
Commit: c3e0a17

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.