Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ailiheizi/workflow-to-skill --skill workflow-to-skill-with-surfacegit clone --depth 1 https://github.com/ailiheizi/workflow-to-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ailiheizi/workflow-to-skill/workflow-to-skill-with-surface)<a href="https://agentmods.dev/skills/ailiheizi/workflow-to-skill/workflow-to-skill-with-surface"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/workflow-to-skill-with-surface/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ailiheizi/workflow-to-skill/workflow-to-skill-with-surface"><img src="https://agentmods.dev/badge/skills/ailiheizi/workflow-to-skill/workflow-to-skill-with-surface.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00092 | $0.03567 |
| Opus 5.5 | $0.00037 | $0.01427 |
| Sonnet 5.5 | $0.00018 | $0.00713 |
| Haiku 4.5 | $0.00009 | $0.00357 |
Grade C, and why
workflow-to-skill-with-surface scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
- collect secrets or grant credentials, permissions, or authority; How it starts
The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow To Skill With Surface
Create one readable workflow Skill and, when supported, a dedicated Prompt Surface around it. The Skill is the single source of workflow method. The Surface only maps structured input to an ordinary Skill message and presents the Harness's ordinary result.
The target Harness loads the Skill, runs the Agent, and invokes existing CLI, MCP, HTTP, API, Dify, n8n, ComfyUI, or other capabilities. Do not create an executor, workflow runtime, Surface runtime, or second state protocol.
Choose The Authoring Action
This Skill supports two ordinary-language authoring actions. The labels are guidance for the Agent, not commands, metadata, a schema, or a second runtime protocol.
- Create: turn a goal and confirmed real capabilities into one candidate
workflow
SKILL.md, then describe the optional native Surface mapping. - Evolve: inspect the current workflow Skill, its Surface mapping, and real execution evidence, then propose the smallest justified Skill or native adapter revision. Evolve does not automatically install, promote, or publish anything.
Use Create when there is no existing Skill to preserve. Use Evolve only when the exact current Skill and usable evidence from a real run, test, artifact, or external result are available. If they are not, report the gap.
Create
goal + real capabilities -> Skill + optional native Surface
Execute
Harness + Agent + existing tools -> ordinary result and evidence
Evolve
current Skill/Surface + evidence -> root-cause review + smallest candidate diff
External gate
independent replay, tests, or review -> accept, reject, or insufficient evidence
Authoring Method
Use one combined authoring and review flow:
- Clarify the workflow outcome, scope, inputs, outputs, side effects, completion criteria, target Harness, and representative success and failure cases. Confirm why a dedicated Surface is useful.
- Inspect real Harness documentation and capabilities. Confirm exact tool bindings, important parameter and result contracts, credential binding names, external workflow identity or version, lifecycle states, and success evidence. Confirm Skill installation and invocation plus the Harness's ordinary message, continuation, and result presentation APIs.
- Present one proposal covering the workflow and Surface together. Label user-confirmed choices, proposed safe defaults, and unresolved material decisions. Include the visible input-to-prompt mapping and Surface boundary.
- Ask for one review of the shared material decisions. Ask again only if a material choice remains unresolved or later changes; do not create a second approval round merely because Surface implementation follows Skill authoring.
- Write the candidate
SKILL.mdafter material choices are confirmed or covered by an explicit unattended policy. The Skill must remain complete and usable without the Surface. - Structurally validate, install, discover, and explicitly invoke the Skill through the Harness's ordinary path when authorized. Confirm the intended candidate was loaded rather than a stale or conflicting copy. Exercise safe success and material stop or failure cases before treating the Surface as ready.
- Implement the Surface only through the target Harness's native UI and ordinary message/result APIs. If those APIs are unavailable, report the adapter gap instead of adding a Workflow-to-Skill runtime.
- Validate input mapping, ordinary invocation-path parity, untrusted input, secrets, result projection, failure behavior, and review continuation when offered. Separate observed behavior from untested claims.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +92 lines · +1 tokens per session 18e5ff79bd07
- 2mo ago First seen · 272 lines · 91 tokens per session scan C daed6a970d7a
workflow-to-skill-with-surface is a skill published in the GitHub repository ailiheizi/workflow-to-skill (2 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 3,567 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it C with 1 finding (harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-loop
Detect requests for iterative autonomous agent loops and route to the appropriate loop executor.
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
aiwg-language-map
AIWG addons + extensions language map — categories, curated discover phrases, and per-bundle pointers covering everything beyond the framework quickrefs.
sdlc-accelerate
End-to-end SDLC ramp-up from idea to construction-ready with automated phase transitions.
steward
Provide provider capability awareness and route commands by answering what the current provider supports natively vs must emulate.
infer-completion-criteria
Infer measurable completion criteria for an agent-loop task from project docs, code, and AIWG standards when the user has not supplied --completion explicitly.