Agent skill

S4H Reasoning Orchestrator

by human-avatar in human-avatar/skills-for-humanity

Takes a situation described in plain English, designs a short sequence of reasoning skills for it and runs them in order, each building on the last.

MITAuto-check passedAgent Workflows

Install S4H Reasoning Orchestrator

skills CLI
$ npx skills add human-avatar/skills-for-humanity --skill s4h -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install human-avatar/skills-for-humanity s4h --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/human-avatar/skills-for-humanity.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/s4h .claude/skills/s4h && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
s4h
GitHub stars
231
Token cost
~2.5k tokens
SKILL.md length
1,133 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Takes a situation described in plain English, designs a short sequence of reasoning skills for it and runs them in order, each building on the last.

  • Works in 5 steps: Intake → Design the Workflow → Present the Plan → …
  • You are unsure how to approach a messy situation
  • SKILL.md covers Your Process and Notes
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

An orchestrator for open-ended problems. You describe your situation and goal; the skill asks about the goal, the obstacle and the decision you are facing, states back its reading in one sentence and checks it with you. It then designs an ordered chain of 2 to 5 skills drawn from across 23 categories and runs each step in turn, passing what each one reveals to the next.

Its design rules put framing before analysis, option generation before evaluation, and an understanding of the people involved before communication or ethics checks. Skills such as assumption-excavator, creativity-alternatives, decision-criteria-weighting and communication-audience-modeling appear as examples. It suits moments like working out where to start, rather than single-tool questions.

When your agent uses it

  • You are unsure how to approach a messy situation
  • A decision needs several kinds of thinking in sequence
  • You want structured reasoning applied from start to finish

Example prompts

  • “Help me think through whether to leave my agency job.”
  • “I need to figure out what to do about a late client project.”
  • “Where do I start with reorganizing my team's responsibilities?”

Requirements

  • The companion skills from the same collection that it chains together

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Intake
  2. Design the Workflow
  3. Present the Plan
  4. Execute — Sequential with Chaining
  5. Synthesize

What it can do on your machine

Read from SKILL.md and the folder at commit a30df8b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

S4H Reasoning Orchestrator loads about 2.5k tokens when it runs. Until then it costs about 104 tokens; SKILL.md has 1,133 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~104
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from human-avatar/skills-for-humanity at commit a30df8b, republished under its MIT licence (© human-avatar). 1,133 words, ~2,455 tokens.

Download SKILL.mdSave it as .claude/skills/s4h/SKILL.md (or your agent's skills folder).
name
s4h
description
Master orchestration skill. Takes any situation in plain English, identifies the underlying goal, designs a multi-skill reasoning workflow, and executes it sequentially — feeding each skill's output into the next. Use when you say 'help me think through this', 'I need to figure out what to do', 'where do I start', or any time you want structured thinking applied end-to-end rather than routed to a single tool.

Human

The master orchestration skill. You describe your situation and goal. This skill designs a tailored reasoning workflow — an ordered sequence of skills from across all 23 categories — then executes each step in sequence, feeding what each step reveals into the next. The result is compounding clarity, not a single tool's take.


Your Process

Step 1: Intake

If the user hasn't described their situation, ask:

What are you trying to achieve? Describe the situation and what a good outcome looks like.

Wait for their response before proceeding. Aim to understand:

  • The goal: what does success look like?
  • The obstacle: what's making this hard?
  • The decision point: what are they about to do, decide, or communicate?

If any of these are unclear after reading their description, ask one targeted follow-up question before designing the plan.

Framing check: Confirm the specific situation before continuing. State what you've identified — the goal, the obstacle, and the decision point — in one sentence, then use AskUserQuestion:

  • Question: "I'm reading this as: [your one-sentence framing of the goal, obstacle, and what they're about to do or decide]. Is that right?"
  • Header: "Framing"
  • Options:
    • Yes — proceed — framing is correct
    • Adjust — one element is off; user will correct it before you continue
    • Reframe — different situation than read; incorporate the correction before proceeding

Step 2: Design the Workflow

Design an ordered sequence of 2–5 skills that together address the goal. Each skill in the sequence should serve a distinct function, and the output of each should meaningfully inform the next.

Sequence design principles:

  • Start with framing before analysis. If the problem framing might be wrong, begin with assumption-excavator or sensory-structured-observation before applying analytical tools.
  • Generate before evaluating. If options are needed, put generation skills (creativity-alternatives, decision-option-mapping, concept-fan) before evaluation skills (decision-criteria-weighting, logic-check, ethics-check).
  • Understand people before designing for them. If the goal involves others' reactions, run emotional-motivation-mapping or communication-audience-modeling before communication-objection-mapping or ethics-impact-scan.
  • Validate before committing. If the goal ends in a decision or action, close with a stress-test skill (decision-premortem-analysis, constraint-hardness-testing, logic-fixer).
  • End with synthesis when the goal is understanding. For exploratory goals, close with a skill that produces a consolidated view (systems-leverage-analysis, narrative-frame-analysis, aesthetic-coherence-check).

Common workflow patterns:

Goal typeTypical sequence
Make a complex decisionassumption-excavator → decision-option-mapping → decision-criteria-weighting → decision-premortem-analysis
Solve a stuck problemassumption-excavator → creativity-lateral-thinking → creativity-alternatives → constraint-hardness-testing
Understand a human situationemotional-motivation-mapping → social-power-mapping → communication-audience-modeling → ethics-empathy-circle
Communicate something difficultcommunication-audience-modeling → communication-objection-mapping → communication-clarity-audit
Evaluate a plan or proposallogic-check → decision-premortem-analysis → ethics-impact-scan → constraint-hardness-testing
Think through a strategysystems-leverage-analysis → strategy-terrain → strategy-positioning → decision-premortem-analysis
Write or reshape somethingwriting-issues → writing-restructure → writing-tone-alignment → writing-line-editing
Understand a system or patternsystems-feedback-mapping → systems-leverage-analysis → historical-precedent-analysis

Use these as starting points. Adapt to the specific situation.

Before narrowing: Show the full candidate workflow to the user before committing to a sequence. Use AskUserQuestion:

  • Question: "I've drafted a workflow of [N] steps. Before I lock it in, are there any steps you'd flag as especially important, any you'd cut, or any angle I've missed?"
  • Header: "Prioritise"
  • Options:
    • Proceed with this sequence — the plan looks right
    • Flag one step — user will name a step to prioritise or adjust
    • Add a missing angle — user will describe a lens or skill not yet included

Step 3: Present the Plan

Show the user the designed workflow before executing. Format it as an ordered list with the rationale for each step and the connection to the next:

Here's the plan I'd run for this:

1. **[skill-name]** — [why we start here; what it will surface]
   → feeds into step 2 by [how its output informs the next step]

2. **[skill-name]** — [what it does given step 1's output]
   → feeds into step 3 by [how its output informs the next step]

3. **[skill-name]** — [what it does given steps 1–2's output]
   [last step: what we'll have at the end]

Then ask: "Run this plan, adjust it, or go straight to a specific step?"

Use AskUserQuestion with:

  • Question: "Ready to run the plan?"
  • Header: "Direction"
  • Options:
    • Run the full plan — Execute each step in sequence now
    • Adjust the plan — Tell me what to change before we start
    • Skip to step [N] — Jump directly to a specific step
    • Just run one skill — Pick the single most useful tool and run it now

Show full SKILL.md (511 more words)Show less
Step 4: Execute — Sequential with Chaining

Run the first skill immediately. After each skill completes, pause and use AskUserQuestion to offer the next move before continuing.

Before each step (after the first), output a brief handoff:

[skill-name] complete. Key finding: [1–2 sentences on what this step revealed and why it matters].

Then use AskUserQuestion to present what to do next:

  • Question: "What's the next move?" (adapt to what was just found — e.g. "We've surfaced 5 assumptions. What now?")
  • Header: "Next"
  • Options: (build dynamically — 2–3 logical next skills given what the current step revealed, plus a wrap-up option)
    • Label: /[skill-name], Description: [one sentence on why this fits as a follow-on and what it will produce given the current output]
    • (repeat for each next skill, up to 3)
    • Label: "Wrap up", Description: "Synthesise what we have so far and close out"

How to select next skill options:

Pick skills that directly consume the current output. Ask: given what we just learned, what's the most useful next question to answer?

If the current step produced…Strong next skills
Surfaced hidden assumptionscreativity-lateral-thinking, decision-option-mapping, constraint-hardness-testing
A list of optionsdecision-criteria-weighting, probability-scenario-weighting, decision-premortem-analysis
A stress-test or failure mapconstraint-workaround-mapping, logic-fixer, strategy-positioning
A map of stakeholders or motivationscommunication-objection-mapping, ethics-empathy-circle, social-incentive-analysis
A logic or argument checklogic-fixer, ethics-check, constraint-hardness-testing
A systems or leverage mapstrategy-positioning, resource-bottleneck-analysis, temporal-horizon-mapping
A creative set of directionsdecision-criteria-weighting, creativity-plus-minus-interesting, constraint-hardness-testing
A communication or framing analysiswriting-argument, narrative-frame-analysis, communication-clarity-audit

When the user selects a skill, run it on the situation context plus all accumulated output so far. Do not re-explain the situation from scratch — build on what prior steps established.

If the user selects "Wrap up" at any point, jump to Step 5.


Step 5: Synthesize

After all steps complete, output a synthesis section:

What the full sequence revealed:

  • List 3–5 findings that emerged from the workflow as a whole — insights that no single step showed on its own.

The key tension or trade-off:

  • Name the central conflict the workflow exposed, if any.

Recommended next action:

  • One concrete thing to do, decide, or communicate based on everything above.

What to revisit:

  • If any assumption or finding in the workflow turned out to be load-bearing but uncertain, flag it here.

Notes

  • The goal drives the plan, not the problem type. The same problem ("I need to decide X") could warrant different workflows depending on whether the goal is speed, thoroughness, buy-in, or ethical grounding.
  • 2–3 steps is often better than 5. A tight two-skill sequence with strong chaining beats a sprawling five-step plan where the connections are thin.
  • Adapt as you go. If step 2 reveals the situation is fundamentally different from what step 1 assumed, redesign the remaining steps rather than running the original plan on stale premises.
  • The handoff is the skill. The value of this workflow is what transfers between steps. Never skip the explicit connection from one step to the next.
  • If the user just wants one skill, use the routing logic from the original human skill — present 3–4 options, let them pick, run it. Not every situation needs orchestration.

© human-avatar, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/s4h of human-avatar/skills-for-humanity.

Open the folder on GitHubat commit a30df8b

Compare with similar skills

S4H Reasoning Orchestrator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

S4H Reasoning Orchestrator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
S4H Reasoning Orchestrator this skillhuman-avatar/skills-for-humanity231—~2.5kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT
Interview Meaddyosmani/agent-skills104k6 repos~3.8kAutomated safety check: PassMIT
OpenSpec Guided OnboardingFission-AI/OpenSpec72k1 repos~4.5kAutomated safety check: PassMIT
Writing Plansgeeksblabla/stateofdev.ma16357 repos~661Automated safety check: PassNone
Subagent Driven DevelopmentAsvarox/allkaraoke26137 repos~1.2kAutomated safety check: PassNone

Similar skills

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Interview Me

    addyosmani/agent-skills

    Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.

    104k GitHub starsUsed in 6 repos~3.8k tokens
    Agent WorkflowsAuto-check passed
  • OpenSpec Guided Onboarding

    Fission-AI/OpenSpec

    Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.

    72k GitHub starsUsed in 1 repo~4.5k tokens
    Agent WorkflowsAuto-check passed
  • Writing Plans

    geeksblabla/stateofdev.ma

    A skill your agent uses when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file…

    163 GitHub starsUsed in 57 repos~661 tokens
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    Asvarox/allkaraoke

    A skill your agent uses when executing implementation plans with independent tasks in the current session

    261 GitHub starsUsed in 37 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Planning With Files

    jd-opensource/JoySafeter

    Implements Manus-style file-based planning for complex tasks.

    314 GitHub starsUsed in 19 repos~1.8k tokens
    Agent WorkflowsAuto-check: notes

More from human-avatar/skills-for-humanity

All 11 skills in this repo
  • Ethics Council

    human-avatar/skills-for-humanity

    Runs a decision or policy question past five ethical frameworks, has them review one another, and returns a chair's synthesis of which values conflict.

    231 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed
  • S4h Logic Council

    human-avatar/skills-for-humanity

    Run a reasoning problem, argument, plan, or decision through a council of 5 logical reasoning advisors who analyze it from distinct reasoning frameworks, peer-review each other, and synthesize a…

    231 GitHub stars~2.4k tokensUpdated 2 mo ago
    Auto-check passed
  • S4h Aesthetic

    human-avatar/skills-for-humanity

    Entry point for the aesthetic toolkit. An agent skill from human-avatar/skills-for-humanity.

    231 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed
  • S4h Aesthetic Coherence Check

    human-avatar/skills-for-humanity

    Tests whether the parts of something form a unified whole — finding the jarring inconsistencies that accumulate when different contributors work without a shared vision.

    231 GitHub stars~1.5k tokensUpdated 2 mo ago
    Auto-check passed
  • S4h Aesthetic Elegance Testing

    human-avatar/skills-for-humanity

    Tests whether a solution is more complex than it needs to be — distinguishing necessary complexity from accidental complexity that accreted over time.

    231 GitHub stars~1.4k tokensUpdated 2 mo ago
    Auto-check passed
  • S4h Aesthetic Pattern Detection

    human-avatar/skills-for-humanity

    Identifies the underlying formal pattern at work — because most successful designs, arguments, and solutions share deep structural patterns, and naming the pattern unlocks the playbook.

    231 GitHub stars~1.5k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about S4H Reasoning Orchestrator

What does S4H Reasoning Orchestrator do?

Takes a situation described in plain English, designs a short sequence of reasoning skills for it and runs them in order, each building on the last. An orchestrator for open-ended problems. You describe your situation and goal; the skill asks about the goal, the obstacle and the decision you are facing, states back its reading in one sentence and checks it with you.

When should I use S4H Reasoning Orchestrator?

S4H Reasoning Orchestrator fits situations like: you are unsure how to approach a messy situation; A decision needs several kinds of thinking in sequence; you want structured reasoning applied from start to finish.

How do I install S4H Reasoning Orchestrator in Claude Code?

Run `npx skills add human-avatar/skills-for-humanity --skill s4h -a claude-code`. Or copy the skill folder (skills/s4h in human-avatar/skills-for-humanity) into .claude/skills/s4h in your project. Claude Code loads it when a task matches its description.

How do I install S4H Reasoning Orchestrator in Codex?

Run `npx skills add human-avatar/skills-for-humanity --skill s4h -a codex`. Or copy the skill folder (skills/s4h in human-avatar/skills-for-humanity) into .agents/skills/s4h in your project. Codex loads it when a task matches its description.

Can I use S4H Reasoning Orchestrator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add human-avatar/skills-for-humanity --skill s4h -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/s4h, .gemini/skills/s4h, .github/skills/s4h and .opencode/skills/s4h in your project.

What does S4H Reasoning Orchestrator need to run?

SKILL.md names no scripts, command-line tools or credentials: S4H Reasoning Orchestrator is instructions for the agent only. Our summary lists: The companion skills from the same collection that it chains together.

Does S4H Reasoning Orchestrator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is S4H Reasoning Orchestrator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does S4H Reasoning Orchestrator use?

S4H Reasoning Orchestrator is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does S4H Reasoning Orchestrator use?

About 2.5k tokens (SKILL.md is roughly 9.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to S4H Reasoning Orchestrator?

Skills that share tags, products or a category with S4H Reasoning Orchestrator: Executing Plans Inline (obra/superpowers, 297k stars), Interview Me (addyosmani/agent-skills, 104k stars), OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 72k stars) and Writing Plans (geeksblabla/stateofdev.ma, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains S4H Reasoning Orchestrator?

human-avatar (a GitHub organization) maintains it in human-avatar/skills-for-humanity, which has 231 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on July 15, 2026.

Source: human-avatar/skills-for-humanity on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.