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 agentmods add skills/agi-comming/functional-skill-creator/migratenpx skills add AGI-comming/functional-skill-creator --skill migrategit clone --depth 1 https://github.com/AGI-comming/functional-skill-creatorWhat 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 | $0.00033 | $0.00990 |
| Opus 5 | $0.00016 | $0.00495 |
| Sonnet 5 | $0.00007 | $0.00198 |
| Haiku 4.5 | $0.00003 | $0.00099 |
Grade A, and why
fskill-creator-migrate 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.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fskill-creator-migrate
Goal
Analyze a large or hard-to-maintain legacy skill directory into structured migration context while preserving behavior. This sub-skill only performs migration pre-analysis and does not directly write final functional skill files; final artifact generation, runtime capability provisioning, file writing, and validation are handled by the main fskill-creator.
Invoked by the main skill when the user has an existing monolithic skill and wants to "refactor into functional", "migrate to functional skill", or "restructure into functions/references/scripts".
Principles
- Preserve existing behavior first, then optimize structure.
- Load the whole legacy skill package, not only
SKILL.md. - Keep source section and file evidence so reviewers can trace migrated content.
- Only output
migration_context; must not directly write target skill files. - Duplicated rules, schemas, and vocabulary move to
reference_plan. - Existing
references/,scripts/, andtools/are inventoried before proposing splits. - Deterministic parsing, formatting, validation, or mechanical transforms are identified as
script_plan, to be generated or preserved later by the main skill. - Optional viewers only enter
tool_plan; final files are generated uniformly by the main skill'sadd_runtime_capabilities.
References
| Resource | Load Timing | Purpose |
|---|---|---|
shared_glossary |
On demand | Stable migration terminology and output fields. |
script_rules |
Before proposing scripts | Rules for deciding what belongs in scripts/. |
External Inputs
| Field | Source | Description |
|---|---|---|
legacy_skill_dir |
user or repository | Path to the legacy skill directory containing SKILL.md. |
legacy_skill_path |
user or repository | Deprecated alias for legacy_skill_dir; may also be a direct path to SKILL.md, which resolves to its parent directory. |
legacy_skill_content |
user or repository | Existing skill markdown content when the directory is inaccessible. |
migration_constraints |
user | Constraints such as preserving file names, tone, or platform rules. |
known_testcases |
user or repository | Existing examples, traces, or expected behaviors. |
existing_scripts |
repository | Existing helper scripts associated with the legacy skill. |
include_viewers |
user | Whether to suggest generating tools/log_viewer.mjs and tools/tester_viewer.mjs. |
script_runtime |
environment | Whether this sub-skill's own Node.js scripts can be run. |
What ships with it
13 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- functions/extract_shared_references.md 1.5 KB
- functions/load_legacy_skill.md 2.2 KB
- functions/map_existing_behavior.md 1.6 KB
- functions/propose_function_split.md 2.8 KB
- logs/runs/.gitkeep 1 B
- references/script-rules.md 1.3 KB
- references/shared-glossary.md 1.6 KB
- scripts/.gitkeep 1 B
- scripts/lint_skill.mjs 2.1 KB runs code
- scripts/migrate_proposal.mjs 8.6 KB runs code
- scripts/migrate_proposal.test.mjs 4.0 KB runs code
- scripts/test_cases.mjs 4.5 KB runs code
- testcases/unit/propose_function_split.basic.case.json 2.0 KB
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.
- 2d ago First seen · 71 lines · 33 tokens per session scan A c80ef3524dcb
fskill-creator-migrate is a skill published in the GitHub repository AGI-comming/functional-skill-creator (359 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 990 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 2026-08-30.
Other skills, from other repositories
LEAP
LEAP builds skills through two pipelines: Branch A distills a skill from raw data, while Branch B combines multiple skills into one. It is called by the main SkillAlchemy workflow. Use when SkillAlchemy requires distillation or fusion.
agentsop-bounded-loop
Universal discipline for any LM-driven loop — agent retries, plan-act-observe, multi-agent handoffs, optimiser passes, test-fix cycles. Encodes the one rule every framework documents quietly and every team relearns expensively: the LM in the loop is NEVER a reliable terminator. Termination must be provided by an…
agentsop-conventions-pinning
SOP for writing, loading, and evolving a project-level convention file (CONVENTIONS.md / CLAUDE.md / .cursor/rules / .clinerules / AGENTS.md) so that a coder-agent reliably respects your codebase's style choices every session. Tool-agnostic; covers the four load mechanics (read-only attachment, ancestor-walk…
agentsop-dify
SOP for building LLM applications on Dify — visual workflow + chatflow + agent + RAG knowledge base + plugin marketplace + observability, self-hostable. Use when shipping LLM apps fast with a "no-code to pro-code" gradient, especially when non-engineers need to co-author the flow.
agentsop-dspy
Operating SOP for DSPy (Stanford NLP) — the declarative framework for "programming, not prompting" language models. Activate when the user says any of: "use DSPy", "compile a prompt", "optimize prompts/programs", "MIPRO/MIPROv2", "BootstrapFewShot", "GEPA", "Signatures + Modules", "teleprompter", "auto-tune prompts…
agentsop-langgraph
Decision protocol for building, debugging, and operating LangGraph-based agent systems. Activates when a coder agent is asked to design a stateful LLM workflow, add human-in-the-loop, choose a multi-agent pattern (supervisor / swarm / hierarchical), pick a checkpoint backend, or migrate a fragile chain into a durable…