Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Design task-local harnesses, eval gates, and reusable skill extraction for Claude dynamic workflow mode and other adaptive agent harnesses.
.claude/skills/dynamic-workflow-mode/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-07 | ✗→✓ | ▲ Improved | — | — |
| case-03 | ✗→✓ | ▲ Improved | — | — |
| case-01 | ✗→✓ | ▲ Improved | — | — |
| case-19 | ✗→✓ | ▲ Improved | — | — |
| case-12 | ✗→✓ | ▲ Improved | — | — |
Use this skill when a coding agent can generate or adapt a task-local harness instead of only following a static command flow. The goal is to turn dynamic workflow mode into a disciplined system: temporary harnesses for one-off work, shared skill extraction for repeated work, and observable control pane checkpoints for teams.
Dynamic workflow mode should produce a task-local harness only when the harness is cheaper and safer than manually driving the same steps. The harness must have:
Use this structure before writing code:
markdown# Dynamic Workflow Harness Objective: - Ship: - Do not ship: Inputs: - Repo or workspace: - External systems: - Credentials policy: Loop: 1. Discover current state. 2. Generate or update the smallest useful artifact. 3. Run eval checks. 4. Record status and handoff. 5. Stop on failed gate, unclear ownership, or unsafe external action. Eval: - Command: - Expected pass signal: - Failure owner: Handoff: - Status: - Evidence: - Next action:
Promote a task-local harness into a shared skill only when at least two of these are true:
When extracting, write the skill first in skills/<name>/SKILL.md. Add command shims only if a legacy slash-entry surface is still required.
Dynamic workflow mode becomes team-usable when it exposes state. Record these checkpoints whenever the task spans more than one session:
If the repo has ECC2 state enabled, prefer adding or reading checkpoints through the ECC control pane or state-store-backed scripts instead of scattering untracked notes.
Every dynamic harness needs a task-specific eval. Pick the cheapest reliable gate:
| Work Type | Eval Gate | | --- | --- | | Code feature | Focused test, lint, coverage, and one integration path | | UI/control pane | Browser smoke with screenshot and overflow/error checks | | Agent workflow | Fixture transcript or seeded work item with expected routing | | Research/content | Source-neutral brief, claim checklist, and publish-ready outline | | Integration | Dry-run command, config validation, and no-secret scan |
Do not claim a dynamic workflow is reusable until the eval can be rerun by another teammate.
Finish with:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-20 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-06 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-07 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-03 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-01 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-09 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-08 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-19 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-25 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-18 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-04 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-12 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-23 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-05 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-14 | pass→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-16 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-22 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-02 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-10 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-11 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-13 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-15 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
case-17 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-21 | fail→fail | — | — | — | — | — | — | — | — | — | — | — | — |
case-24 | fail→pass | — | — | — | — | — | — | — | — | — | — | — | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 25 cases were attempted, and 23 counted toward the lift figure. The other 2 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +44 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
The per-case answers from this run were removed by the retention sweep, so the case table below shows the verdicts without the text either arm produced. The counts above were recorded at the time and are unaffected. Answers are now kept for 180 days.
Other measured skills in the registry, with their headline benchmark lift.