Tessl • The management layer for AI agent skills

The body delivers an executable, well-sequenced workflow with concrete CLI commands, state handling, and output templates that assume Claude's competence. Deductions are minor: some redundancy between the Guardrails and step-6 pause conditions, and pause-and-ask error handling instead of explicit verify/re-check steps.

Dimension	Reasoning	Score
Conciseness	The body is procedurally dense with no explanations of concepts Claude already knows, assuming competence throughout. It falls short of 5 because the Guardrails section noticeably restates the pause conditions already given in step 6 ("If task is ambiguous, pause and ask" vs "Pause if: Task is unclear → ask for clarification"), which could be trimmed.	4 / 5
Actionability	Provides copy-paste-ready commands (`openspec list --json`, `openspec status --change "<name>" --json`, `openspec instructions apply --change "<name>" --json`), explicit state handling (blocked, all_done), concrete checkbox update syntax (`- [ ]` → `- [x]`), and filled-in output templates covering implementation, completion, and pause cases.	5 / 5
Workflow Clarity	A clear 7-step sequence with numbered steps, state-based branching, pause conditions, and required progress/status displays. Not 5 because error handling is pause-and-ask rather than an explicit validate→fix→retry feedback loop, and there is no step to re-run `openspec status` to verify final state; not capped at 3 since this is neither a destructive nor batch operation.	4 / 5
Progressive Disclosure	With no bundle files present, all content lives appropriately in a single well-sectioned SKILL.md (Steps, Outputs, Guardrails, Fluid Workflow Integration), relying on the CLI for dynamic instructions rather than inlining them. Not 5 because the skill exceeds the under-50-line simple-skill case and the three full output templates could be condensed into a more scannable reference block.	4 / 5
	Total	17 / 20 Passed

Description

78%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, uses third person, and clearly answers both what the skill does and when to use it with explicit trigger phrases. Its main weakness is thin capability coverage — a single action verb with no elaboration of the supporting workflow (change selection, context reading, progress tracking).

Suggestions

Enumerate 1-2 more concrete capabilities in the first sentence, e.g. "Select an active change, read its context files, and implement its tasks sequentially, marking progress as you go."

Add natural trigger synonyms such as "execute tasks", "finish tasks", or "resume implementation" to broaden when-matching without adding vagueness.

Mention the OpenSpec change workflow context (e.g. "when the user wants to work through an OpenSpec change's task list") to sharpen distinctiveness against generic implementation skills.

Dimension	Reasoning	Score
Specificity	"Implement tasks from an OpenSpec change" names the domain and a single core action, matching the anchor for naming a domain with 1-2 concrete actions but not comprehensive coverage. It does not reach 4 because no additional capabilities (selecting changes, reading context, tracking progress) are enumerated.	3 / 5
Completeness	Clearly answers "what" ("Implement tasks from an OpenSpec change") and "when" with an explicit "Use when..." clause containing concrete trigger phrases ("start implementing, continue implementation, or work through tasks"), matching the top anchor.	5 / 5
Trigger Term Quality	"start implementing, continue implementation, or work through tasks" provides good natural-phrase coverage a user would plausibly say. Not 5 because common synonyms like "execute tasks", "finish tasks", or "resume implementation" are missing.	4 / 5
Distinctiveness Conflict Risk	The OpenSpec-specific domain gives it a clear niche with minimal conflict risk, but "implementing tasks" is generic enough to overlap with other implementation/continuation skills, matching the "mostly distinct" anchor rather than fully distinct.	4 / 5
	Total	16 / 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: dwmkerr/openspec-flow
Path: .claude/skills/openspec-apply-change/SKILL.md
Revision: bb205d6

Reviewed: 11 hours ago

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.

openspec-apply-change

Table of Contents

Is this your skill?