CtrlK
BlogDocsLog inGet started
Tessl Logo

conductor

Working with Conductor (conductor.build), the parallel-agent app. Creating local and cloud workspaces, the conductor CLI and public API, auth, sessions and messages, deep links, settings and setup scripts, environment variables, and writing briefs for handed-off agents. Use when asked to open, create, rename, archive, or inspect a workspace or session, spin up parallel agents, kick off or hand off work in Conductor, query conductor sql, debug a deep link that did not work, fix Conductor auth, or explain the local-versus-cloud distinction.

76

Quality

94%

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

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.

A dense, executable reference that leads with the decisive local-vs-cloud fact, provides copy-paste commands, and pairs risky operations (deep-link creation) with explicit verification and troubleshooting checklists. It is slightly below peak conciseness due to narrative asides and dated breadcrumbs, and lacks local bundle files for progressive disclosure.

Suggestions

Move dated breadcrumbs like 'Verified 2026-08-16' and 'CLI 0.80.1' into a short 'Verification notes' or 'As of' section so the main flow stays lean and aging markers are isolated.

Trim editorial asides ('That was a dead end', 'do not bother reverse-engineering') or consolidate them into a single 'Pitfalls' note to save tokens without losing the warning.

Consider extracting the long deep-link grammar and API endpoint table into a references/ file (e.g. DEEPLINKS.md) referenced one level deep, improving progressive_disclosure toward 5.

DimensionReasoningScore

Conciseness

Mostly lean and assumes competence — no basic concept explanations — but a few embedded narrative asides (e.g. 'That was a dead end', 'do not bother reverse-engineering') and dated breadcrumbs ('Verified 2026-08-16', 'CLI 0.80.1') could be trimmed or moved to a notes section.

4 / 5

Actionability

Fully executable, copy-paste-ready commands throughout — the Python urllib snippet for building deep links, `conductor workspaces create` with full flags, auth/sql/session commands — and specific examples cover the common cases including the jq alternative.

5 / 5

Workflow Clarity

Multi-step processes are explicitly sequenced with validation: 'When the deep link appears not to work' gives an ordered checklist, 'open exit status proves nothing' mandates verification via `git worktree list`, and the brief-writing section is a numbered list with checkpoints (verify the fix before writing the brief).

5 / 5

Progressive Disclosure

Well-structured with clear section headers and an in-skill Docs list of external URLs; no bundle files exist so references are external links rather than one-level-deep local files, which is appropriate but keeps it just below the well-signaled-local-reference anchor.

4 / 5

Total

18

/

20

Passed

Description

100%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.

A strong, third-person description that pairs a comprehensive capability list with an explicit, natural-phrase 'Use when' trigger clause. It is specific, well-triggered, and clearly distinct from other skills.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities (create/rename/archive workspaces and sessions, query conductor sql, fix auth, debug deep links) and a long 'what' list (CLI, public API, auth, sessions, messages, deep links, settings, env vars, briefs) — comprehensive coverage.

5 / 5

Completeness

Explicitly answers 'what' (the long capability sentence) and 'when' via an explicit 'Use when asked to...' clause with concrete trigger phrases; both halves are clearly and concretely present.

5 / 5

Trigger Term Quality

Natural user phrases abound — 'open, create, rename, archive, or inspect a workspace or session', 'spin up parallel agents', 'kick off or hand off work', 'query conductor sql', 'debug a deep link that did not work', 'fix Conductor auth' — matching how a user would actually phrase the need.

5 / 5

Distinctiveness Conflict Risk

The Conductor.build / parallel-agent niche plus product-specific triggers (conductor sql, deep links, local-vs-cloud) make it clearly distinguishable from generic skills; minimal conflict risk.

5 / 5

Total

20

/

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
freekmurze/dotfiles
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.