CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

orchestrating-work

Use when facing complex tasks that benefit from decomposition into focused subtasks delegated to specialist workers

Quality

74%

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 ./skills/orchestrating-work/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

70%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 well-structured instruction skill with an exemplary three-phase workflow (explicit checkpoints, feedback loops, checklists) and a strong worked example. Its main weaknesses are redundant sections that could be trimmed, and a progressive-disclosure failure: all three referenced worker prompt-template files are absent from the bundle, undermining both actionability and navigation.

Suggestions

Create the referenced ./workers/coder-prompt.md, ./workers/researcher-prompt.md, and ./workers/reviewer-prompt.md files (or inline the templates) so the delegation phase is executable as written.

Remove the dot-graph decision tree or the 'Use when / Don't use' bullet lists — they encode the same decision logic twice.

Fold the 'Key Principles' section into the phase descriptions it restates (e.g., move manager responsibilities into Phase 1/3) to cut redundancy.

DimensionReasoningScore

Conciseness

The dot-graph decision tree duplicates the 'Use when / Don't use' bullets that immediately follow it, and the 'Key Principles' section restates Phase 1-3 content (e.g., 'Never do the work - Only plan, delegate, verify'), so the body could be tightened. Most of the document is genuinely instructive rather than padded explanation of concepts Claude already knows, so it sits above noticeably-verbose (2) but below efficient (4).

3 / 5

Actionability

Concrete, specific guidance throughout: numbered phase steps, named worker roles (coder/researcher/reviewer), a fully worked rate-limiter example with a Definition of Done checklist, and red-flag remedies. Not a 5 because the most execution-critical artifact — the worker prompt templates — is deferred to ./workers/coder-prompt.md, ./workers/researcher-prompt.md, and ./workers/reviewer-prompt.md, none of which exist in the bundle, leaving a real gap at dispatch time.

4 / 5

Workflow Clarity

Three clearly sequenced phases with explicit validation checkpoints ('Check for INCAPABLE - Reassign or handle differently', 'Check Definition of Done - All criteria met'), a feedback loop for error recovery (INCAPABLE → reassign/rethink), and a Red Flags section for course correction. This matches the anchor for clear sequence with explicit validation, feedback loops, and checklists; not a 4 because checkpoints are explicit rather than implicit.

5 / 5

Progressive Disclosure

References to ./workers/coder-prompt.md, ./workers/researcher-prompt.md, and ./workers/reviewer-prompt.md are clearly signaled and only one level deep, but no workers/ directory exists in the bundle, so the disclosure chain breaks at the exact point a user would need it. The body itself is well-sectioned (not a monolithic wall), so it scores above 2, but references to entirely missing files are more than the 'minor organization gaps' of a 4.

3 / 5

Total

15

/

20

Passed

Description

66%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 solid description with an explicit 'Use when' clause, third-person voice, and good domain vocabulary. It is held back by thin action coverage (only decompose/delegate, omitting plan/verify/synthesize) and a broad 'complex tasks' trigger that risks overlap with neighboring planning and parallel-agent skills.

Suggestions

List the full action set — e.g., 'Decompose complex requests into focused subtasks, delegate each to a specialist worker subagent, verify results against a Definition of Done, and synthesize outputs' — to raise specificity and completeness.

Add concrete trigger variations such as 'multi-part requests', 'tasks with 3+ independent subtasks', or 'when parallel specialist work would help' to sharpen the 'when' clause and reduce overlap with generic planning skills.

DimensionReasoningScore

Specificity

The description names the domain and two concrete actions — 'decomposition into focused subtasks' and 'delegated to specialist workers' — matching the anchor for 1-2 concrete actions without comprehensive coverage. Not a 4 because it omits several specific actions the skill actually performs (planning, verification, synthesis); not a 2 because the delegation mechanism is named concretely rather than generically.

3 / 5

Completeness

Both 'what' ('decomposition into focused subtasks delegated to specialist workers') and an explicit 'when' clause ('Use when facing complex tasks that benefit from decomposition') are present. Not a 5 because the 'when' stays at the abstract level of 'complex tasks' without concrete trigger phrases (e.g., multi-part requests, 3+ subtasks, needing parallel workers); not a 3 because the 'when' is explicit, not merely implied.

4 / 5

Trigger Term Quality

Good keyword coverage of natural orchestration vocabulary: 'complex tasks', 'decomposition', 'focused subtasks', 'delegated', 'specialist workers' — a user needing this skill would plausibly say several of these. Not a 5 because common variations like 'break down', 'multi-part', 'parallel', or 'orchestrate' are absent; not a 3 because coverage goes well beyond one or two generic keywords.

4 / 5

Distinctiveness Conflict Risk

The 'complex tasks that benefit from decomposition' trigger is somewhat specific but overlaps with planning, workflow, and parallel-agent skills (the body itself lists 'superpowers:dispatching-parallel-agents' and 'superpowers:writing-plans' as neighbors). Not a 4 because no cue in the description distinguishes it from those closely related skills; not a 2 because the specialist-worker delegation framing is more specific than generic skill descriptions.

3 / 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

tslateman/bach

Path

skills/orchestrating-work/SKILL.md

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.