Skillify

A guided process for turning a repeated workflow into a reusable skill file. It interviews the user, writes the instructions, and saves them for later sessions.

In plain words
What is it for?
Use it to capture a recurring development or project workflow as a SKILL.md file that an agent can load and follow.
Why use it?
It removes the need to explain the same multi-step process every time it is needed.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/cocorof/geny-executor/skillify
Any agent
npx skills add CocoRoF/geny-executor --skill skillify
Clone the repo
git clone --depth 1 https://github.com/CocoRoF/geny-executor

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,222 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.01222
Opus 5 $0.00018 $0.00611
Sonnet 5 $0.00007 $0.00244
Haiku 4.5 $0.00004 $0.00122

Measured 2d ago against content hash efdb777bc85e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Skillify scanned grade A with 0 findings 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 2d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

src/geny_executor/skills/bundled/skillify/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skillify — capture a repeated workflow as a skill

You are going to interview the user, distill what they keep doing into a SKILL.md, and write it to the right place on disk. The output lives at ~/.geny/skills/<id>/SKILL.md (user-scope) or <project>/.geny/skills/<id>/SKILL.md (project-scope) depending on how broadly the workflow applies.

Step 1 — Sniff the context

Before asking anything, glance at the recent conversation. The workflow being captured is probably something the user just did (or just asked to redo). If you can already infer the shape, lead with a one-sentence summary and ask the user to confirm.

# Where would the project-scope skill go?
[ -d .geny/skills ] || mkdir -p .geny/skills
echo ".geny/skills/ ready under $(pwd)"

Step 2 — Interview

Ask, in this order, one question at a time. Wait for an answer before the next question. Don't ask all at once — operators get overwhelmed and answer poorly.

  1. What should this skill do, in one sentence? This becomes the description frontmatter field. Push back gently if the answer is vague — "produces a report" is too broad; "produces a markdown summary of changed files between two git refs" is right.

  2. What's a short id? kebab-case, ≤ 32 chars, must match [a-z0-9][a-z0-9_-]*. Suggest one based on the description if the user shrugs.

  3. What arguments does it take? Ask for argument names and a one-line hint. If none, that's fine — many skills are parameterless.

  4. Which tools does it need? Pick from the host's actual tool roster (Read / Write / Bash / Edit / Grep / Glob, plus any custom). Default to [Read, Bash] if the user is unsure.

  5. When should the model use it? This is the when_to_use field — extra discovery copy beyond the description. Examples: "When the user asks for a release-note draft."

  6. User scope or project scope? User scope if it applies regardless of which repo they're in (e.g. "PR draft generator", "verify"). Project scope if it depends on this codebase's layout (e.g. "run the project's specific test sweep").

Read the full file on GitHub · 132 lines

Changes

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.

  1. 2d ago First seen · 132 lines · 36 tokens per session scan A efdb777bc85e

Subscribe to this mod's changes

Skillify is a skill published in the GitHub repository CocoRoF/geny-executor (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,222 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

hephaestus-network

Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.

agentlas-ai/Agentlas-OS · 75 tokens

routing-card-authoring

Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.

agentlas-ai/Agentlas-OS · 68 tokens

hephaestus-upload

Use when the user types $hephaestus-upload, /hep-upload, or /agentlas-upload, or asks to upload, publish, or list an Agentlas agent or team. Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate.

agentlas-ai/Agentlas-OS · 67 tokens

session-agent-builder

Turn the current interactive conversation into an owner-reviewed reusable Agentlas agent; accept JSON or JSONL only for explicit terminal and automation runs.

agentlas-ai/Agentlas-OS · 31 tokens

team-builder-packaging

Use when generating or auditing a multi-role agent team package with orchestrator, PM Soul, Memory Curator, Policy Gate, workers, eval, QA, handoffs, and runtime adapters.

agentlas-ai/Agentlas-OS · 43 tokens

hephaestus-graph

Use when the user types /hep-graph or asks to create, list, inspect, or request a run of an Agentlas automation graph.

agentlas-ai/Agentlas-OS · 35 tokens