Tessl • The management layer for AI agent skills

SkillPublic

ulw-execute

Executes a written ulw-plan work plan with Boulder state, evidence ledger, worktree discipline, and parallel subagents. Use when the user says ulw-execute or asks to run a .omo/plans plan.

Quality

84%

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

Quality

Content

77%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 an exceptionally actionable and well-sequenced orchestration procedure with real validation feedback loops. Its weaknesses are verbosity (repeated mandates and run-on rule sentences) and the absence of any progressive disclosure — harness compatibility tables, QA channel specs, and the delegation router would be better split into reference files.

Suggestions

Split harness-specific material (the Codex v1/v2 tool translation tables and tier mapping) into a references/ file and keep only the routing decision rule in SKILL.md.

Move the Manual-QA channel specs and the 9 ultraqa class trigger map into reference files, summarizing just the channel-selection rule inline.

State the orchestrator-never-implements rule once (in Hard rules) and reference it from Phase 3 instead of repeating the full mandate three times; break the goal-discipline and Phase 4 stop-rule run-on sentences into numbered sub-rules.

Dimension	Reasoning	Score
Conciseness	Mostly dense, operative rule-making rather than explanation of known concepts, but the orchestrator-never-implements rule is repeated three times and several sections are overlong compound sentences (goal-discipline step 3, the Phase 4 stop-rule paragraph) that could be materially tightened.	3 / 5
Actionability	Fully concrete throughout: exact commands ('git worktree add <repo>-wt/<plan>-<wave> <branch>'), copy-paste JSON templates (boulder.json, DoneClaim/AdversarialVerify), literal tool invocations, an exact QA script command, and a full trigger map for the 9 ultraqa classes.	5 / 5
Workflow Clarity	A clear five-phase sequence with explicit validation: five gates per checkbox, an adversarial verification feedback loop that re-dispatches executors on non-confirmed verdicts, explicit stop rules, and blocked-state ([~]) handling.	5 / 5
Progressive Disclosure	Good in-file structure with clear section headers, but no bundle files exist and content that clearly belongs in separate references (Codex v1/v2 harness compatibility tables, Manual-QA channel specs, delegation router) is inlined in one ~245-line file.	3 / 5
	Total	16 / 20 Passed

Description

87%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: it states a concrete capability set and gives explicit, natural trigger phrases for a well-defined niche. The only weakness is thin synonym coverage and use of internal jargon ('Boulder state') that a non-initiated invoker may not map to intent.

Dimension	Reasoning	Score
Specificity	Names the core action plus four concrete mechanisms ('Boulder state, evidence ledger, worktree discipline, and parallel subagents'), matching several specific actions with minor gaps; 'Boulder state' is internal jargon that keeps it from comprehensive self-explanatory coverage.	4 / 5
Completeness	Explicitly answers both what ('Executes a written ulw-plan work plan with...') and when ('Use when the user says ulw-execute or asks to run a .omo/plans plan') with concrete trigger phrases.	5 / 5
Trigger Term Quality	'Use when the user says ulw-execute or asks to run a .omo/plans plan' gives exact, natural triggers for this niche, but common variations like 'run the work plan' or 'resume the plan' are missing.	4 / 5
Distinctiveness Conflict Risk	'ulw-plan work plan', 'ulw-execute', and '.omo/plans' define a clear niche with distinct triggers and virtually no overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: code-yeongyu/oh-my-openagent
Path: packages/shared-skills/skills/ulw-execute/SKILL.md
Revision: 687f5af

Reviewed: 3 days ago

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.

ulw-execute

Table of Contents

Is this your skill?