CtrlK
BlogDocsLog inGet started
Tessl Logo

orchestrator

Turn the current Codex thread into a coordination thread that routes per-branch implementation work to durable reusable child threads without worktrees.

62

Quality

73%

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 ./.agents/skills/orchestrator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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, highly actionable contract: exact commands, exact tool names, a copy-paste child prompt, a decision-tree routing workflow with explicit failure guards, and a success checklist. Its only weaknesses are mild repetition of the worktree rule and a single-file structure that could split templates into a reference, neither of which meaningfully hurts usability.

DimensionReasoningScore

Conciseness

The body is lean, imperative, and assumes Claude's competence — no concepts are over-explained — with only minor redundancy: the worktree prohibition is stated in the Core Contract ('Do not create or suggest worktrees'), the child prompt template ('Do not create a worktree'), and Success Criteria ('Worktrees are not created'). That repetition could be trimmed but the rest earns its tokens, so it sits above anchor 3 and below the perfectly lean 5.

4 / 5

Actionability

Guidance is copy-paste ready: exact commands ('$orchestrator on/off/status'), seven exact tool names to search for, a ready-to-send child prompt template, a thread title format ('<BRANCH-OR-TICKET> <short task title>'), and a concrete status table schema. These cover the common creation, routing, and status cases the skill will actually face.

5 / 5

Workflow Clarity

Routing Rules is a 9-step sequence with explicit decision points (per-branch vs not, branch key resolution fallbacks, found vs not found) and error-recovery guards: 'If mode state is unclear, ask once before executing locally', 'If these tools are not available, stop and report', and a required child closeout report of branch key, PR URL, blockers, and next owner. The Success Criteria section functions as an explicit checklist. This is not the 4 anchor because checkpoints are not merely 'mostly present' — every risky branch (missing mapping, missing tools, unclear mode, concurrent same-checkout work) has an explicit guard.

5 / 5

Progressive Disclosure

The skill is a single ~150-line file with no bundle directories (references/, scripts/, assets/ do not exist), and the body makes no dangling file references — all sections are well-labeled and navigable. It is not the 5 anchor because that expects clearly signaled one-level-deep references splitting detail out (e.g. the child prompt template or status table could live in a reference file), though at this length a single well-organized file is defensible.

4 / 5

Total

18

/

20

Passed

Description

58%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 states a concrete, distinctive capability in a single efficient sentence, but it omits any explicit 'use when' trigger guidance and relies on internal jargon rather than natural user phrases, so it is unlikely to be reliably surfaced by a user's request. Adding a trigger clause and natural synonyms would lift completeness and trigger-term quality substantially.

Suggestions

Append an explicit trigger clause, e.g. 'Use when the user asks to orchestrate, delegate, or route branch/PR work to child threads, or wants this thread to only coordinate.'

Include natural user phrasings as triggers (e.g. 'delegate', 'dispatch', 'spin up a child thread for this branch') instead of only internal terms like 'durable reusable child threads'.

Briefly enumerate the visible capabilities (mode on/off/status, per-branch routing, thread reuse, status reporting) to make the 'what' comprehensive rather than single-sentence.

DimensionReasoningScore

Specificity

The description names several concrete actions — 'Turn the current Codex thread into a coordination thread', 'routes per-branch implementation work to durable reusable child threads', 'without worktrees' — which goes beyond the 1-2-action anchor but stops short of comprehensive coverage of what the skill does (mode toggles, status reporting, thread reuse, safety rules).

4 / 5

Completeness

The 'what' is clear (turn the thread into a coordination thread routing work to child threads), but there is no 'Use when...' clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. It is not a 2 because the 'what' is specific and concrete, not vague.

3 / 5

Trigger Term Quality

Relevant keywords exist ('Codex thread', 'coordination thread', 'child threads', 'worktrees') but they lean toward internal jargon ('durable reusable child threads', 'per-branch'), and natural user phrases like 'orchestrate', 'delegate', or 'dispatch work' are missing. It clearly lists relevant terms yet lacks common variations, so it is not the sparse 2 or the well-covered 4.

3 / 5

Distinctiveness Conflict Risk

'Codex thread', 'per-branch', 'child threads', 'without worktrees' carve out a distinct orchestration niche with mostly unique triggers, with only minor overlap risk against generic delegation/subagent skills. It is not a 5 because the trigger vocabulary is jargon-adjacent and a user asking broadly to 'delegate' or 'parallelize' work could plausibly match other skills.

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
udecode/plate
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.