$ loading_
Design adaptive agent workflows with eval gates and reusable skill extraction.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "dynamic-workflow-mode" skill from askskill: 1. Download https://raw.githubusercontent.com/affaan-m/ECC/main/skills/dynamic-workflow-mode/SKILL.md 2. Save it as ~/.claude/skills/dynamic-workflow-mode/SKILL.md 3. Reload skills and tell me it's ready
Design a dynamic workflow mode task skeleton for a coding assistant, including task decomposition, local tool use, stage checkpoints, fallback strategies, and criteria for when to extract a reusable skill.
A structured workflow plan describing stage responsibilities, transition conditions, and skill extraction criteria.
I have an AI agent that automatically generates data reports. Help me design eval gates to check data completeness, conclusion consistency, and format compliance, and define pass thresholds and failure actions for each gate.
An actionable eval-gate design with metrics, thresholds, trigger points, and remediation steps.
Analyze this multi-step customer support agent workflow and identify sub-tasks that should become reusable skills, such as intent classification, knowledge retrieval, and response polishing. Provide module boundaries, input/output definitions, and reuse recommendations.
A skill extraction checklist that defines each module’s responsibility, interface, and ideal use cases.
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:
# 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:
…
Retrieve and update Jira issues, analyze requirements, and streamline team workflows.
Design security and risk controls for autonomous trading agents with transaction authority
Compare prediction-market baskets with research notes to find gaps and alignment.
Coordinate behavior-preserving code refactors with tests, review, and gated commits.
Accelerate large-scale data pipelines, backfills, and syncs without sacrificing correctness.
Use Exa neural search for web, code, company, and people research.
Create, refine, and troubleshoot AI skills, specs, invocation, and compatibility.
Automatically distill, update, and prune reusable skills from real coding sessions.
Build and iterate meta-harness scaffolding for fixed models via propose-score-Pareto loops.
Design, evaluate, refine, and package AI skills with an architecture-first workflow.
Adds reusable Claude Code workflows with agents, skills, hooks, and commands.
Portable workspace for coding agents with issue-driven collaboration and session continuity.