CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

ulw-loop

A goal-like loop that decomposes work into systematic, evidence-bound ultrawork steps. Use when the user wants a goal loop or durable, checkpointed execution.

Quality

81%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is ulw-loop in code-yeongyu/oh-my-openagent

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 exemplary operational overlay: it stays compact while packing in exact commands, tool-call shapes, error codes, and validation gates, and it delegates the bulk workflow to real, well-organized one-level-deep reference files. Its only weakness is a handful of overlong run-on rules that could be tightened. Scores are strong across all dimensions.

DimensionReasoningScore

Conciseness

The body is dense, rule-driven, and teaches only environment-specific facts Claude could not know (CLI commands, tool surface, error codes) — no padding or generic concept explanations. A few passages could be trimmed, e.g. the ~70-word run-on Non-Negotiable about goal registration and the git tree-binding parenthetical, so it matches anchor 4 (efficient, minor over-explanation) rather than anchor 5.

4 / 5

Actionability

Guidance is copy-paste ready throughout: exact CLI invocations ("omo-agent-toolkit ulw-loop create-goals", "--session-id <id>", "git rev-parse --short \"HEAD^{tree}\""), full tool-call shapes ("spawn_agent({\"task_name\":\"<lower_snake_id>\"...\"fork_turns\":\"none\"})"), and concrete error-code contracts (ULW_LOOP_SESSION_SCOPE_REQUIRED, ULW_LOOP_CODEX_GOAL_JSON_INVALID). The tool-mapping table covers the common cases (spawn, re-task, send, wait, enumerate, stop), matching anchor 5.

5 / 5

Workflow Clarity

"Required First Steps" gives an ordered bootstrap sequence with an explicit precondition ("before running any ULW command or recording evidence"), validation gates are pervasive ("Record only after cleanup receipts exist", tree-hash evidence binding with a re-run rule, "lands when its own evidence is captured and its gates are green"), and feedback loops exist for error recovery (fallback/respawn rules, lead-resolved conflicts). Despite batch delegation and merge operations, validation is explicit, so the destructive/batch cap does not apply — this matches anchor 5.

5 / 5

Progressive Disclosure

The bundle structure is exactly as signaled: SKILL.md states "The full workflow lives in references/full-workflow.md. Read only the sections needed for the current phase", and both referenced files (full-workflow.md, 272 lines; define-goal.md, 107 lines) exist with the named sections (Bootstrap, Execution Loop, Manual-QA channels, Stop Rules) verified present. References are one level deep (the only cross-reference is the sibling define-goal.md), the split is appropriate (bulk detail like quality-gate JSON shapes lives in the reference), matching anchor 5.

5 / 5

Total

19

/

20

Passed

Description

62%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 answers both 'what' and 'when' in third person with an explicit trigger clause and a fairly distinct niche, but the capability statement is thin — one jargon-flavored action instead of a concrete action list — and the trigger coverage is narrow. It sits comfortably in the middle-upper range of the rubric.

Suggestions

Replace the jargon-heavy capability sentence with 2-3 concrete named actions, e.g. "Registers goals with success criteria, delegates code edits and QA to subagents, and records verifiable evidence per criterion" (specificity).

Broaden the 'Use when' clause with natural synonyms users would actually say, such as "long-running tasks", "resumable or checkpointed work", or "evidence-based delivery" (trigger_term_quality).

Spell out what 'ultrawork steps' means in plain terms or drop the term, since it is internal vocabulary a user would never say (specificity, distinctiveness).

DimensionReasoningScore

Specificity

Names the domain ("goal-like loop") and one semi-concrete action ("decomposes work into systematic, evidence-bound ultrawork steps"), but "ultrawork" is internal jargon and "systematic" is a buzzword qualifier rather than additional actions. It fits anchor 3 (domain plus 1-2 concrete actions, not comprehensive): above anchor 2 because a real action is stated, below anchor 4 because only one action is listed.

3 / 5

Completeness

Both parts are present: what ("decomposes work into systematic, evidence-bound ultrawork steps") and an explicit when ("Use when the user wants a goal loop or durable, checkpointed execution"). Fits anchor 4 — the 'when' could name more concrete triggers and the 'what' leans on jargon, keeping it below anchor 5; it is above anchor 3 because the 'when' is explicit, not weakly implied.

4 / 5

Trigger Term Quality

The trigger clause "Use when the user wants a goal loop or durable, checkpointed execution" offers two relevant phrases but misses natural variations the body itself lists ("long-running", "checkpointed delivery", "ulw", resuming work). Matches anchor 3 (some relevant keywords, missing common variations or synonyms); not 4 because coverage is narrow.

3 / 5

Distinctiveness Conflict Risk

The niche ("goal loop", "durable, checkpointed execution") is distinctive with low overlap against typical skills, matching anchor 4 (mostly distinct, minor overlap risk). Not anchor 5 because "durable... execution" is broad enough to collide with a generic durable-execution or planning skill.

4 / 5

Total

14

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

Repository

code-yeongyu/lazycodex

Path

plugins/omo/components/ulw-loop/skills/ulw-loop/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.