@human-avatar/skills-for-humanity 1.0.0

package/skills/decision/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: decision
+description: "Entry point for the decision toolkit. Routes to the right decision skill based on your situation. Use when you say 'decision', 'help me decide', 'should I', 'which option', 'what are my choices', 'what could go wrong', 'is this reversible', or want decision help without knowing which specific tool fits."
+---
+
+# Decision
+
+Applies structured decision thinking to any choice. Diagnoses what kind of decision work is needed and applies the right tool.
+
+## Which tool fits
+
+| You need to... | Tool |
+|---|---|
+| Make sure you're seeing all the real options | option-mapping |
+| Compare options against weighted criteria | criteria-weighting |
+| Stress-test a decision by imagining it failed | premortem-analysis |
+| Calibrate how much process this decision deserves | reversibility-analysis |
+
+## Routing Decision
+
+- **About to decide between 2 options — may be missing others** → option-mapping first
+- **Options are visible, need to compare them systematically** → criteria-weighting
+- **Leaning toward a direction, want to stress-test it** → premortem-analysis
+- **Unsure how much time to spend on this decision** → reversibility-analysis
+- **Unclear** → option-mapping; the option space is almost always narrower than it should be
+
+## Confirm Direction
+
+After diagnosing which tool fits, present the recommendation before executing:
+
+> My read: **[diagnosed tool]** — one sentence on why it fits.
+
+- **A) Yes, run that tool**
+- **B) Show me all options** — list every skill in this category with one-line descriptions
+- **C) Quick version** — lighter-weight alternative for this situation, if one exists
+- **D) Re-diagnose** — describe the situation differently for a second read
+
+Wait for their selection before proceeding.
+
+---
+
+## Option Mapping
+
+*Ensures all real options are visible before choosing.*
+
+Counter the false dichotomy: the first two options that come to mind are rarely all that exists. Generate options across three levels: (1) direct solutions to the stated problem, (2) alternative framings of the problem that suggest different solutions, (3) options that combine or transcend the initial set. Apply the deliberate quota: find at least 5 options. Don't evaluate until the inventory is complete.
+
+**Output:** Option inventory (5+ minimum), including options that reframe the problem, with brief descriptions. No evaluation yet — just the full map.
+
+---
+
+## Criteria Weighting
+
+*Runs a weighted multi-criteria analysis.*
+
+Step 1: List what actually matters for this decision. Step 2: Weight each criterion by importance (1-5 scale). Step 3: Score each option on each criterion (1-5). Step 4: Calculate weighted scores. Step 5: Check the winner against intuition — if the numbers say X but your gut says Y, that gap is information worth understanding, not a flaw in the method.
+
+**Output:** Weighted decision matrix, ranked options, and an interpretation of whether the quantitative result matches or challenges intuition.
+
+---
+
+## Premortem Analysis
+
+*Imagines the decision was made and failed — then diagnoses why.*
+
+Set the scene: it's 12 months from now. The decision was made, and it failed badly. Write the failure story: what went wrong? Be specific — not "it didn't work" but the actual mechanism of failure. Generate 5+ distinct failure paths. Now: which failure modes are most probable? Which are most damaging if they occur? Which can be mitigated before committing?
+
+**Output:** 5+ failure paths, ranked by probability and severity. For each high-priority failure mode: the mitigation that reduces it. The adjusted decision recommendation.
+
+---
+
+## Reversibility Analysis
+
+*Categorises a decision by reversibility to apply the right level of process.*
+
+Two-way door decisions (easily reversible) should be made quickly with less process — the cost of deliberating exceeds the cost of being wrong. One-way door decisions (hard or impossible to reverse) deserve thorough analysis. Classify this decision: what would it take to undo it? How quickly? At what cost? Many decisions that feel irreversible aren't. Many that feel casual are more binding than they appear.
+
+**Output:** Decision classification (reversibility score 1-5), what undoing it would require, and the recommended level of process given that classification.

package/skills/decision-criteria-weighting/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: decision-criteria-weighting
+description: "Runs a weighted multi-criteria analysis — making explicit what matters, how much, and how each option performs against it. Triggers: 'weighted decision matrix', 'multi-criteria analysis', 'help me choose between', 'compare these options', 'decision matrix'."
+---
+
+# Decision Criteria Weighting
+
+Intuitive decisions fail when too many criteria are in play and their relative importance
+isn't made explicit. This skill forces that explicitness. The goal is not to replace
+judgment — it is to make the judgment visible enough to inspect, challenge, and defend.
+
+---
+
+## Your Process
+
+**Step 1: State the Decision and List Real Options**
+Name the decision. List the actual options being considered — not aspirational ones. If an
+option isn't genuinely available, remove it before it contaminates the analysis.
+
+**Step 2: Identify 4-8 Criteria**
+Name the criteria that define a good outcome for this specific decision. Criteria should
+be independent (not measuring the same thing twice), observable (you can score against
+them), and genuinely relevant (removing one would change the analysis).
+
+**Step 3: Weight the Criteria**
+Distribute exactly 100 points across the criteria. This forces trade-offs — you cannot
+weight everything highly. If everything matters equally, the distribution reveals a
+failure to think through what actually matters most.
+
+**Step 4: Score Each Option**
+Score each option on each criterion from 1 to 5. Do this before calculating totals — the
+sequence matters. Scoring after you see where things are headed is reverse-engineering to
+confirm a preference, which defeats the exercise.
+
+**Step 5: Calculate Weighted Scores**
+Weighted score = sum of (weight × score) for each criterion. Calculate for all options.
+
+**Step 6: Sense-Check**
+If the math agrees with your intuition, good. If it disagrees, investigate: is the
+intuition catching something the criteria missed, or is the intuition rationalising a
+preference? Either is possible. Don't dismiss either.
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Weights only** — establish criteria priorities before scoring any options
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Decision:** [Statement]
+
+**Criteria and weights:**
+
+| Criterion | Weight (total = 100) |
+|-----------|----------------------|
+| | |
+
+**Scored matrix:**
+
+| Option | [Criterion 1] (×W) | [Criterion 2] (×W) | ... | Weighted Total |
+|--------|-------------------|-------------------|-----|----------------|
+| | | | | |
+| | | | | |
+
+**Sense-check:**
+> [Does the result match intuition? If not — what is the intuition picking up that the
+> matrix doesn't capture, or what is the intuition getting wrong?]
+
+**Recommendation:**
+> [Option name] — [one sentence rationale]
+
+---
+
+## Notes
+
+The value of this exercise is in the weighting step, not the scoring. Most decision
+disagreements are disagreements about what matters, not about how options perform.
+Making weights explicit moves the conversation to the right place.

package/skills/decision-option-mapping/SKILL.md

@@ -0,0 +1,93 @@
+---
+name: decision-option-mapping
+description: "Ensures all real options are visible before choosing — countering the false dichotomy that limits consideration to the first two options that came to mind. Triggers: 'what are all the options', 'false dichotomy check', 'expand the option set', 'what else could we do', 'options inventory'."
+---
+
+# Decision Option Mapping
+
+The options people choose between are usually not all the options that exist — they are
+the first options that were named, which then anchored the frame. This skill expands the
+option set before analysis begins, using four specific moves that reliably surface options
+the natural framing excludes.
+
+---
+
+## Your Process
+
+**Step 1: State the Decision and Currently-Considered Options**
+Write the decision as currently framed and list all options currently on the table. Don't
+filter yet — include the options even if they seem weak.
+
+**Step 2: Challenge the Frame**
+Is this decision actually forced? Are you choosing between options A and B because those
+are the real options, or because those are the options that were generated first? What
+would have to be true for there to be no decision to make?
+
+**Step 3: Four Expansion Moves**
+
+**(a) Expand**: Generate 3 more ways to achieve the underlying goal. Not variations on
+existing options — genuinely different approaches. Ask: if none of the current options
+existed, what would we try?
+
+**(b) Defer**: Is "decide later" viable? At what cost? Deferral is a real option — it
+has costs and benefits like any other. When can this be decided without foreclosing
+anything important?
+
+**(c) Hybrid**: Can elements of multiple options be combined? Hybrids often emerge when
+options are treated as mutually exclusive when they aren't.
+
+**(d) Reframe**: If the goal were slightly different, what options appear? Sometimes
+the option set is limited by the goal framing, not the constraints.
+
+**Step 4: Add Viable New Options**
+From the four moves, add the options that are genuinely viable. Discard the ones that
+don't survive basic scrutiny — not to narrow prematurely, but to keep the set useful.
+
+**Step 5: Recommend Next Step**
+With the expanded set, recommend which analytical tool to apply: decision-criteria-
+weighting (multiple comparable options), decision-reversibility-analysis (one option being
+considered), or decision-premortem-analysis (a direction already being leaned toward).
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Hidden options only** — surface the options not currently being considered
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Decision as framed:** [Statement]
+**Currently-considered options:** [List]
+
+**Frame challenge:**
+> [Is this decision forced? What assumptions are built into the current option set?]
+
+**Expanded option set:**
+
+| Option | Source (original / expand / defer / hybrid / reframe) | Viable? | Reason |
+|--------|------------------------------------------------------|---------|--------|
+| | | | |
+| | | | |
+
+**Options to add to the decision:**
+> [Bulleted list with one-line rationale each]
+
+**Recommended next step:**
+> [Which analytical skill to apply, and to which expanded option set]
+
+---
+
+## Notes
+
+The most commonly missed option is deferral. "Decide now" is itself a choice with costs —
+urgency is often assumed rather than real, and deferral with a defined review point is
+frequently the most rational option on the table.

package/skills/decision-premortem-analysis/SKILL.md

@@ -0,0 +1,86 @@
+---
+name: decision-premortem-analysis
+description: "Imagines the decision has been made and failed — then diagnoses why. Breaks the commitment bias that prevents honest risk assessment after a direction is chosen. Triggers: 'pre-mortem', 'imagine this failed', 'what could go wrong', 'assume this doesn't work', 'failure mode analysis'."
+---
+
+# Decision Premortem Analysis
+
+Once a direction is chosen, commitment bias makes honest risk assessment nearly impossible
+— the mind starts defending the decision rather than evaluating it. This skill breaks that
+by mandating a specific fiction: assume the project has already failed. Then ask why.
+The pessimism is not optional — it is the mechanism.
+
+---
+
+## Your Process
+
+**Step 1: State the Decision and Intended Outcome**
+Write the decision clearly and the specific outcome it is supposed to produce. Include
+the timeline and the measurable definition of success.
+
+**Step 2: Project to Failure**
+Enter the failure frame. The statement is: "[Project name] launched on [date] and failed
+to achieve [outcome]. Here is what went wrong." Write this as if reporting a post-mortem,
+not brainstorming risks. The past-tense fiction reduces defensive filtering.
+
+**Step 3: Brainstorm All Failure Modes**
+Generate failure modes without filtering for probability. Encourage pessimism. For each
+failure mode, ask: how would this actually unfold? What would be the first sign? What
+would make it worse?
+
+**Step 4: Group Failures by Type**
+- **Execution failures**: we had the right model of the world but did it wrong —
+  timing, resourcing, coordination, quality.
+- **Assumption failures**: we did it right but our model of the world was wrong —
+  the market, the users, the technology, the dependencies.
+- **Unknown failures**: we didn't anticipate this category of problem at all.
+
+**Step 5: Pre-emptive Action per Top Failure Mode**
+Identify the 3-5 most significant failure modes (highest probability × severity). For
+each: what single action, taken now, most reduces the probability or severity of this
+failure?
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Top 3 failure modes only** — highest probability × severity combinations, skip the full inventory
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Decision and intended outcome:**
+> [Statement + timeline + measurable success definition]
+
+**Failure modes (all generated):**
+
+| Failure mode | Type (Execution / Assumption / Unknown) | Probability | Severity |
+|-------------|----------------------------------------|-------------|----------|
+| | | | |
+| | | | |
+
+**Top 3-5 failure modes with pre-emptive actions:**
+
+| Failure mode | Why it's significant | Pre-emptive action |
+|-------------|---------------------|-------------------|
+| | | |
+| | | |
+
+**Assumption inventory (things that must be true for this to work):**
+> [Bulleted list — these are the highest-leverage unknowns to validate early]
+
+---
+
+## Notes
+
+Assumption failures are the most dangerous category because they are invisible until
+something breaks. The pre-mortem's most durable output is often the assumption inventory —
+which assumptions, if wrong, would make the entire direction invalid?

package/skills/decision-reversibility-analysis/SKILL.md

@@ -0,0 +1,88 @@
+---
+name: decision-reversibility-analysis
+description: "Categorises a decision by reversibility and applies the appropriate level of process rigour. Triggers: 'is this reversible', 'how much should I think about this', 'one-way door', 'two-way door', 'decision type', 'how committed is this'."
+---
+
+# Decision Reversibility Analysis
+
+Most people apply the same amount of thinking to every decision. This is wrong in both
+directions: it produces analysis paralysis on easy reversible choices, and recklessness on
+decisions that cannot be undone. The right question before deciding is not "what should
+I choose?" — it is "how much should I invest in choosing?"
+
+---
+
+## Your Process
+
+**Step 1: State the Decision**
+Write the decision clearly. Include what is actually being committed to — not the
+framing, the underlying commitment.
+
+**Step 2: Assess Reversal Cost**
+If this decision turns out to be wrong, how expensive is it to undo? Consider: financial
+cost, time cost, relationship or trust cost, technical debt introduced, market position
+lost, and optionality foreclosed. Be concrete — not "expensive" but "six months of
+re-architecture and two broken partnerships."
+
+**Step 3: Classify — Type 1 or Type 2**
+- **Type 1 (one-way door)**: reversing is very costly or practically impossible. Wrong
+  here means significant, durable damage.
+- **Type 2 (two-way door)**: can be walked back at low cost if wrong. A review point or
+  small experiment can reveal the error before it compounds.
+
+**Step 4: Apply the Appropriate Process**
+- Type 1: slow down. Consult broadly. Surface dissent. Apply full analytical rigour.
+  Set explicit criteria for what "good" looks like before committing.
+- Type 2: decide quickly. Set a review point. Move. Do not let this consume the time
+  budget of a Type 1 decision.
+
+**Step 5: Flag Misclassification Risk**
+Some decisions feel reversible but aren't. Network effects, sunk cost psychology,
+technical lock-in, and relationship damage can make nominal two-way doors practically
+one-way. Identify these explicitly.
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Reversibility verdict only** — is this reversible or not, and what that means for how much deliberation it deserves
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Decision:** [Statement — including the underlying commitment]
+
+**Reversal cost:**
+> [Concrete statement of what undoing this actually costs — time / money /
+> relationships / technical / optionality]
+
+**Classification:** Type 1 (one-way door) / Type 2 (two-way door)
+
+**Recommended process level:**
+
+| Type | Process |
+|------|---------|
+| Type 1 | Slow down — broad consultation, explicit success criteria, full rigour |
+| Type 2 | Decide quickly — set review point, move, learn |
+
+**Misclassification risk:**
+> [Reasons this might be harder to reverse than it appears — or easier]
+
+**Recommendation:**
+> [Classification + what to do next based on it]
+
+---
+
+## Notes
+
+The most expensive error is treating a Type 1 decision as Type 2 — deciding quickly on
+something that cannot be undone. But the second-most expensive error is treating Type 2
+decisions as Type 1, because the opportunity cost of delay is real and cumulative.

package/skills/emotional/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: emotional
+description: "Entry point for the emotional intelligence toolkit. Routes to the right emotional skill based on your situation. Use when you say 'emotional', 'why are they behaving like this', 'what motivates them', 'why the resistance', 'what do they really want', 'trust issues', or want emotional/interpersonal reasoning applied without knowing which specific tool fits."
+---
+
+# Emotional
+
+Applies emotional intelligence to interpersonal and organizational situations. Diagnoses what kind of emotional reasoning is needed and applies the right tool.
+
+## Which tool fits
+
+| You need to... | Tool |
+|---|---|
+| Understand what genuinely drives someone's behavior | motivation-mapping |
+| Diagnose why people are resisting or not engaging | resistance-diagnosis |
+| Find what someone actually cares about beneath their stated position | stakes-mapping |
+| Map what's building or eroding trust in a relationship | trust-audit |
+
+## Routing Decision
+
+- **Behavior is hard to predict or incentives seem misaligned** → motivation-mapping
+- **People are pushing back, won't get on board** → resistance-diagnosis
+- **Negotiation or alignment is failing — stated positions aren't moving** → stakes-mapping
+- **A relationship or team has trust problems** → trust-audit
+- **Unclear** → stakes-mapping; understanding what's really at stake usually clarifies everything else
+
+## Confirm Direction
+
+After diagnosing which tool fits, present the recommendation before executing:
+
+> My read: **[diagnosed tool]** — one sentence on why it fits.
+
+- **A) Yes, run that tool**
+- **B) Show me all options** — list every skill in this category with one-line descriptions
+- **C) Quick version** — lighter-weight alternative for this situation, if one exists
+- **D) Re-diagnose** — describe the situation differently for a second read
+
+Wait for their selection before proceeding.
+
+---
+
+## Motivation Mapping
+
+*Maps what genuinely drives different people.*
+
+Go beyond job descriptions and stated reasons. For each person: what do they actually want from their work (autonomy, mastery, belonging, recognition, security, impact)? What do they fear? What stories do they tell about themselves — and does this decision threaten or reinforce those stories? Stated motivations and real motivations often diverge; the gap is where behavior becomes hard to predict.
+
+**Output:** Per-person motivation map: genuine drivers, fears, identity narrative, and how this situation activates or threatens each.
+
+---
+
+## Resistance Diagnosis
+
+*Diagnoses why people are resisting.*
+
+Resistance is information, not obstruction. It always has a source. Classify the resistance: (1) Misunderstanding — they don't understand what's being asked, (2) Disagreement — they understand but think it's wrong, (3) Fear — they understand but are worried about consequences, (4) Values conflict — they oppose the underlying direction, not just this decision. Each type requires a completely different response; treating all resistance as obstruction makes it worse.
+
+**Output:** Resistance classification, the specific source underneath the pushback, and the appropriate response for that type.
+
+---
+
+## Stakes Mapping
+
+*Maps what each stakeholder actually cares about beneath their stated position.*
+
+In any negotiation, alignment challenge, or disagreement, stated positions are rarely the real issue. For each stakeholder: what is their stated position? What underlying interest does it serve? What would they actually need to see to move? Addressing stated positions while missing real stakes accomplishes nothing — the agreement collapses or the compliance is hollow.
+
+**Output:** Per-stakeholder map: stated position, underlying interest, real stakes, and the minimum conditions for genuine alignment.
+
+---
+
+## Trust Audit
+
+*Maps what is building and eroding trust in a relationship or situation.*
+
+Trust degrades silently until it fails loudly. Audit trust across four dimensions: (1) Competence — do they believe you can deliver? (2) Integrity — do they believe you mean what you say? (3) Benevolence — do they believe you have their interests at heart? (4) Reliability — do they trust your follow-through? For each dimension: what recent events support or undermine trust? What actions would rebuild it?
+
+**Output:** Trust audit across four dimensions, with specific evidence for each. Priority actions that most efficiently rebuild trust.

package/skills/emotional-motivation-mapping/SKILL.md

@@ -0,0 +1,95 @@
+---
+name: emotional-motivation-mapping
+description: "Maps what genuinely drives different people — beyond stated reasons and job descriptions. Use when incentives seem misaligned or individual behaviour is hard to predict. TRIGGERS: 'what motivates them', 'motivation map', 'why are they behaving like this', 'what drives this person', 'understand the incentives'."
+---
+
+# Emotional Motivation Mapping
+
+People tell you what they think they should want. They behave according to what they
+actually want. When the two diverge — when stated goals and actual behaviour don't
+match, when someone ostensibly aligned keeps producing friction — the problem is almost
+always that the real motivators haven't been surfaced. This skill maps them across
+three levels: extrinsic, intrinsic, and social.
+
+---
+
+## Your Process
+
+**Step 1: List Individuals or Groups**
+Name each person or group whose motivation needs mapping. Be specific — "the
+engineering team" and "the engineering manager" may have completely different dominant
+motivators. Split when in doubt.
+
+**Step 2: Extrinsic Motivators**
+What external rewards and penalties shape their behaviour? Consider: compensation
+structure (base, bonus, equity), formal recognition mechanisms (awards, visibility,
+attribution), advancement paths available, job security, and the specific performance
+metrics they're formally evaluated against. These are the motivators the system is
+designed to create — they may or may not match what actually drives behaviour.
+
+**Step 3: Intrinsic Motivators**
+What internal drives are they pursuing independently of external reward? Consider:
+mastery (the desire to get better at something they care about), autonomy (control
+over how and when they work), purpose (feeling the work connects to something that
+matters), belonging (being part of a team or mission they identify with). These often
+operate below the surface but produce the most durable behaviour.
+
+**Step 4: Social and Political Motivators**
+What does their standing among peers require? Consider: status within the group and
+how they maintain or advance it, key relationships they're protecting and what those
+require, reputation they're managing across different audiences, being seen as
+credible, indispensable, or ahead of the curve.
+
+**Step 5: Dominant Motivator**
+Given all three categories, what is the single strongest driver for this person or
+group? The dominant motivator is the one that, if frustrated, would produce the most
+significant behavioural change — or that, if served, would unlock the most
+discretionary effort.
+
+**Step 6: Situation Assessment and Alignment Recommendations**
+Does the current situation reward or punish their dominant motivator? Be specific
+about the mechanism. If it punishes — and many organisations inadvertently punish
+their people's dominant motivators — describe what specific changes would bring
+motivators into alignment with the desired outcome.
+
+---
+
+## Human Check-in
+
+Before proceeding, ask the user:
+
+**How do you want to run this?**
+
+- **A) Full analysis** — complete all steps, reasoning shown throughout
+- **B) Key findings only** — bottom-line output, skip step-by-step detail
+- **C) Core driver only** — the deepest motivation beneath the stated reasons
+- **D) Refine the framing** — adjust what we're analyzing before starting
+
+Proceed based on their choice.
+
+## Output Format
+
+**Motivation Map**
+
+| Person/Group | Extrinsic | Intrinsic | Social/Political | Dominant Motivator |
+|---|---|---|---|---|
+| [name/role] | [key external rewards/penalties] | [mastery/autonomy/purpose/belonging] | [status/relationships/reputation] | [single strongest driver] |
+
+**Situation Assessment**
+For each dominant motivator: does the current situation reward or punish it? Name
+the specific mechanism — the exact way the setup serves or frustrates the dominant
+motivator.
+
+**Alignment Recommendations**
+What specific changes would align each dominant motivator with the needed outcome?
+Prioritise by likely influence on actual behaviour.
+
+---
+
+## Notes
+
+Dominant motivators rarely change — but the situation around them can be redesigned.
+Look for the misalignment first; don't assume the solution is to change the person.
+The most common failure is designing incentive systems around extrinsic motivators
+while the dominant motivator is intrinsic — the system pulls in the wrong direction
+and produces compliance without commitment.