acceptance-orchestrator

Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.

Quality

43%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/acceptance-orchestrator/SKILL.md

Quality

Content

62%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured orchestration skill with a clear state machine, explicit stop/escalation conditions, and good human gate definitions. Its main weaknesses are the lack of concrete executable examples or commands, and the reliance on sub-skill references that aren't provided or linked. Some generic boilerplate (Limitations section) could be trimmed.

Suggestions

Provide concrete examples of the output contract (e.g., a sample status report with actual evidence fields filled in) to improve actionability.

Include or link to the referenced sub-skill files (create-issue-gate, closed-loop-delivery, verification-before-completion) so the progressive disclosure structure is navigable rather than opaque.

Remove or significantly trim the Limitations section, as its content is generic guidance Claude already follows by default.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some sections that could be tightened—'When to Use' bullets partially restate the description, and the 'Limitations' section contains generic advice Claude already knows (e.g., 'stop and ask for clarification if required inputs are missing'). The state machine list and workflow are mostly lean.	2 / 3
Actionability	The workflow provides a clear sequence of steps and the output contract specifies concrete fields, but there are no executable code examples, no concrete commands, and the sub-skill references (e.g., 'create-issue-gate', 'closed-loop-delivery') are opaque without definitions or examples. The guidance is structured but not copy-paste ready.	2 / 3
Workflow Clarity	The state machine is explicitly defined with named states, the workflow steps are clearly sequenced with numbered phases, stop conditions and escalation criteria are explicit, and human gates provide clear validation checkpoints. The feedback loop (2 full rounds before escalation, PR polling backoff) is well-specified.	3 / 3
Progressive Disclosure	The skill references multiple sub-skills (create-issue-gate, closed-loop-delivery, verification-before-completion) which implies a layered structure, but no bundle files are provided and there are no links to actual files. The content is well-sectioned but everything is inline in a single file with no way to navigate to the referenced sub-skills.	2 / 3
	Total	9 / 12 Passed

Description

25%Scale 1-3

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 relies heavily on abstract process terminology without specifying concrete actions the skill performs. While it includes a 'Use when...' clause, the trigger language is formal jargon rather than natural user language. The description would benefit significantly from listing specific capabilities and using terms users would naturally employ.

Suggestions

Replace abstract workflow phases with concrete actions, e.g., 'Reads GitHub/Jira issues, writes code, creates pull requests, runs tests, deploys changes, and verifies acceptance criteria.'

Add natural trigger terms users would actually say, such as 'automate', 'end-to-end', 'fix this issue', 'implement feature', 'autonomous coding', 'hands-off', or 'fully automated'.

Strengthen the 'Use when...' clause with specific scenarios, e.g., 'Use when the user wants a coding task handled autonomously from start to finish, including when they say "just handle it", "implement this end to end", or "take this issue and ship it".'

Dimension	Reasoning	Score
Specificity	The description uses abstract language like 'coding task', 'issue intake', 'implementation', 'review', 'deployment', and 'acceptance verification' but does not list any concrete actions. These are high-level workflow phases, not specific capabilities like 'create pull requests', 'run tests', or 'deploy to staging'.	1 / 3
Completeness	The description has a 'Use when...' clause addressing when to use the skill, but the 'what' is only vaguely implied through the workflow phases rather than explicitly stated. The 'when' trigger is present but overly abstract ('coding task should be driven end-to-end').	2 / 3
Trigger Term Quality	The terms used ('issue intake', 'acceptance verification', 're-intervention') are process jargon rather than natural keywords a user would say. Users are more likely to say things like 'fix this bug end to end', 'implement this feature', or 'handle this issue' rather than these formal workflow terms.	1 / 3
Distinctiveness Conflict Risk	The 'end-to-end' and 'minimal human re-intervention' framing provides some distinctiveness from narrower coding skills, but 'coding task' and 'implementation' are broad enough to overlap with many other development-related skills.	2 / 3
	Total	6 / 12 Passed

Validation

90%

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 — 10 / 11 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	10 / 11 Passed

Repository: administrakt0r/AI-Agents-Safe-Coding-Skills
Path: skills/acceptance-orchestrator/SKILL.md
Commit: 900c504

Reviewed: 16 minutes 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.