CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

parallel-execution-optimizer

Speed up a task by turning it into a dependency graph of parallel lanes with a lane matrix, batched reads and checks, write surfaces isolated by file, worktree, branch, or service, and a final verification table. Use when the user wants a task done much faster through parallel work, concurrent agents, batched tool calls, isolated worktrees, many independent verification lanes, or bounded homogeneous work that reuses shared preparation while record operations remain sequential, without losing correctness.

Quality

79%

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/parallel-execution-optimizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

63%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 parallel-execution core of the skill is excellent: a crisp pattern, a concrete lane matrix, real safety gates, and a strong output template. Quality degrades in the second half, where the bounded-homogeneous-work material drifts into abstract, jargon-heavy prose and an evaluation-criteria section that reads as internal eval-harness leakage (GROUP_A/GROUP_B, journal, ECC) rather than guidance for a practitioner.

Suggestions

Move the Bounded Homogeneous Work deep-dive (planner/executor walkthrough, connector-change resume protocol, evaluation criteria) into a references/ file such as bounded-work.md, keeping a 5-10 line summary and a clear one-level-deep pointer in SKILL.md.

Delete or rewrite the Evaluation Criteria section: it references undefined artifacts (GROUP_A/GROUP_B, 'the existing journal', ECC) and instructs how to evaluate the skill rather than how to execute it, adding tokens without actionable value.

Replace abstract vocabulary ('bounded homogeneous work', 'accepted mapping/contract version', 'owner-defined completion unit') with one or two concrete task examples (e.g., updating 200 records through an API) so the pattern is recognizable without domain-specific context.

DimensionReasoningScore

Conciseness

Core Pattern, Lane Matrix, Execution Rules, Output Shape, and Failure Modes are lean, but the 'Evaluation Criteria' section (~20 lines referencing GROUP_A/GROUP_B, an 'existing journal', and ECC) is meta-commentary about evaluating the skill rather than executable instruction, and the connector-change resume section is padded with undefined artifacts — mostly efficient with unnecessary content that could be cut or tightened.

3 / 5

Actionability

Concrete guidance throughout: a 7-step core pattern, a filled-in lane matrix template, a planner/executor walkthrough with explicit carry-forward state, and a copy-ready output shape; the journal/GROUP_A material and abstract phrases like 'accepted mapping/contract version' keep it below fully-executable coverage.

4 / 5

Workflow Clarity

The main workflow is a clear numbered sequence with explicit validation ('Merge only after evidence shows the lanes are compatible') and real feedback loops for batch/destructive work ('Stop on a conflict; if no such protection is available, do not write', 'reconcile an uncertain outcome before any retry'), but the connector-change resume flow and evaluation-criteria material obscure the sequence enough to miss the top anchor.

4 / 5

Progressive Disclosure

No bundle files exist and the document is well-sectioned, but at ~160 lines over half the body is the 'Bounded Homogeneous Work' deep-dive (planner/executor walkthrough, resume protocol, evaluation criteria) inlined in SKILL.md — a distinct sub-topic that should live in a separate reference file with a brief summary and pointer here.

3 / 5

Total

14

/

20

Passed

Description

88%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 description: concrete actions, an explicit 'Use when' clause with multiple natural trigger phrases, and a recognizable speed-through-parallelism niche. The only weakness is a stretch of jargon ('bounded homogeneous work that reuses shared preparation while record operations remain sequential') that no user would naturally say when invoking the skill.

DimensionReasoningScore

Specificity

Lists multiple distinct concrete actions — 'turning it into a dependency graph of parallel lanes', 'lane matrix', 'batched reads and checks', 'write surfaces isolated by file, worktree, branch, or service', 'final verification table' — covering the workflow end to end, matching the comprehensive-coverage anchor rather than the minor-gaps anchor.

5 / 5

Completeness

Explicitly answers both 'what' (dependency graph of parallel lanes, lane matrix, batched reads, isolated write surfaces, verification table) and 'when' via a concrete 'Use when the user wants a task done much faster through...' clause with multiple trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases users would say — 'much faster', 'parallel work', 'concurrent agents', 'isolated worktrees' — but the trigger 'bounded homogeneous work that reuses shared preparation while record operations remain sequential' is insider jargon rather than natural user vocabulary, so coverage is good but not comprehensive.

4 / 5

Distinctiveness Conflict Risk

The parallel-lanes/concurrent-agents/worktree niche is mostly distinct with only minor overlap risk against general orchestration or efficiency skills; 'speed up a task' alone is broad enough to prevent a clear-niche score of 5.

4 / 5

Total

18

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository

affaan-m/ECC

Path

skills/parallel-execution-optimizer/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.