skill-work-slicing

Break a plan or spec into vertical slices that each declare what blocks them — use when work is agreed but not yet cut into fileable pieces

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-work-slicing/SKILL.md

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 tight, actionable instruction skill with concrete tracker commands, explicit stop/checkpoint validation, and a clear output contract. It earns strong marks across all dimensions with only minor organization and detail gaps.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence — concrete slice examples and tracker commands earn their place — with only minor trim opportunities (the decision-records paragraph and the host-adapter/Codex provenance notes), fitting 'efficient; minor instances of over-explanation'.	4 / 5
Actionability	Concrete executable commands are given ('bd create --parent=<id>', 'bd dep add <issue> <depends-on>', 'bd ready', 'gh') plus a 4-step workflow and a precise Output Contract; as an instruction-only skill the guidance is actionable with only minor gaps (full ticket-body command flags and 'gh issue create' specifics are not spelled out).	4 / 5
Workflow Clarity	A clear sequenced workflow pairs with explicit validation gates — 'Stop and recut if any slice cannot be verified on its own', 'Stop if the blocking graph has a cycle', 'Confirm the slice list with the user before filing' — plus a Verification checklist and a write-blocked feedback path, satisfying the batch/destructive validation requirement; it falls short of anchor 5 because validation lives in separate Stop/Verification sections rather than inline validate→fix→retry steps.	4 / 5
Progressive Disclosure	No bundle files exist, so this scores the body's structure: well-organized sections (When To Use, When Not To Use, Inputs, Workflow, Output Contract, Verification) with a clearly signaled one-level reference ('see skills/blocks/codex-host-adapter.md'); it is appropriately self-contained rather than reaching the multi-file reference pattern of anchor 5.	4 / 5
	Total	16 / 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 cleanly states what the skill does and gives a specific, state-based trigger condition in third person. Its main weaknesses are the missing common user synonyms (tickets/tasks) and only two named actions.

Suggestions

Add the natural synonyms users actually say — 'tickets', 'tasks', 'epics', 'stories' — so the skill triggers when someone asks to break work into tickets rather than only 'slices'.

Name one or two more concrete actions (e.g., 'file them in the tracker' and 'map blocking dependencies') to move specificity from two actions toward 'several'.

Strengthen the 'when' clause with concrete trigger keyword phrases (e.g., 'use when the user asks to break a plan or spec into tickets or tasks') to reach the explicit-trigger standard of the top anchor.

Dimension	Reasoning	Score
Specificity	Quotes 'Break a plan or spec into vertical slices' and 'declare what blocks them' — two concrete actions in the planning domain, matching the '1-2 concrete actions, not comprehensive' anchor; it does not reach anchor 4's 'several specific actions' since only two actions are named.	3 / 5
Completeness	Both 'what' ('Break a plan or spec into vertical slices that each declare what blocks them') and 'when' ('use when work is agreed but not yet cut into fileable pieces') are present; the when is a specific condition but lacks the concrete trigger keyword phrases that would lift it to anchor 5.	4 / 5
Trigger Term Quality	Relevant terms appear ('plan or spec', 'vertical slices', 'fileable pieces', 'blocks') but the most natural user synonyms — 'tickets', 'tasks', 'epics', 'stories' — are absent, fitting 'some relevant keywords but missing common variations or synonyms'.	3 / 5
Distinctiveness Conflict Risk	The trigger 'work is agreed but not yet cut into fileable pieces' carves a clear niche distinct from generic planning; minor overlap risk remains with closely related skills the body itself names (skill-pressure-test, /octo:parallel), fitting 'mostly distinct; minor overlap risk'.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: skills/skill-work-slicing/SKILL.md
Commit: 0093dab

Reviewed: 5 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.