BC orch-pipeline
Shared orchestration engine behind the orch-* skill family — the gated Research-Plan-TDD-Review-Commit pipeline, size classifier, agent and command map, and two human gates (plan approval, commit confirmation) that orch-* operation skills delegate to. Use indirectly via orch-add-feature, orch-fix-defect, orch-change-feature, orch-refine-code, or orch-build-mvp; read directly only when adding an orch operation or tuning shared phases.
This is not a standalone skill but the engine powering the orch-* operation family. Promises unified pipeline logic: Research → Plan → TDD → Review → Commit with two human gates (plan approval, commit confirmation) and task size classifier.
Grade B, quality 80/100. No critical findings, but process score hit only 54—likely incomplete docs or test coverage. Single file, sparse tokens (1455), no scripts. Runs on all major platforms: Claude, Cursor, DeepSeek, and the rest.
Already using orch-add-feature or orch-fix-defect? Then this engine runs in the background—no need to install separately. Writing your own orch operation? Read it to avoid duplicating gate and classification logic. Direct editing requires understanding the family's architecture.
Shared orchestration engine behind the orch- skill family — the gated Research-Plan-TDD-Review-Commit pipeline, size classifier, agent and command map, and…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
The same skill appears in 1 more place: ECC
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 5 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 19 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1455 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +3Description length 437: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 19 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.