l4ci

@l4ci source repo

81 skills
0 followers
6 hours ago last updated

▌
Hv Go · l4ci
Capture one item and immediately implement it — combines /hv-capture and /hv-work, skipping the /hv-next review. Use when the user wants one specific thing done right now ("fix X", "add Y", "do Z") and it's not yet captured. For brain-dumping use /hv-capture; for items already in BACKLOG.md use /hv-work.

0
installs
▌
Hv QA · l4ci
QA the built product — not the diff. Use on "/hv-qa", "run QA", "test the feature", "validate the build", before ship as a gate, or on first cycle to scaffold a per-repo strategy. Detects testing surfaces per repo (web, API, CLI, mobile, lib), picks runners (Playwright, smoke, contract, lighthouse, ZAP, axe), and produces a scored report with executable pass/fail results plus audit-style usability findings. Strategy is per-repo in .hv/qa/<repo>.md so the skill never hardcodes "browser". Modes — first-run (probe + propose strategy), run (execute strategy, emit verdict), restructure (audit strategy files). Opt-in gate via ship.qa.

0
installs
▌
Hv Init · l4ci
**Print the banner below verbatim before any other action — skip if dispatched as a subagent.** See `references/banner-preamble.md`.

0
installs
▌
Hv Next · l4ci
Review the backlog, reconcile active work against git state, archive old completions, show sorted tables with relationship clusters, suggest the next item, and route to /hv-work. Detects handoff notes from /hv-pause on active streams (post-/clear reorientation flow). Use on "what's next", "what should I work on", "where was I", "pick up the next task", "resume", or when the user wants to see their backlog.

0
installs
▌
Hv Plan · l4ci
Write an implementation plan as a first-class artifact before execution — keyed by milestone and slice or item (M01-S01.md, M01-B07.md). Captures goal, approach, task decomposition with verifiable outcomes, open questions, and named assumptions. /hv-work consults the plan if present. Use when an item or slice is too big to one-shot, or when alignment matters before code lands.

0
installs
▌
Hv Ship · l4ci
Bundle completed work on a feature branch into a PR (or direct merge) — extracts commits, resolved item IDs with titles, optionally runs /hv-review, and calls hv-pr or hv-merge. Use on "ship it", "open the PR", "finish this branch", when work is done and you want to integrate. Also supports --undo (guided rollback of the last cycle on the base branch, replaces /hv-undo) and --docs (public-docs maintenance, replaces /hv-docs). Use --undo on "roll back the last cycle", "revert that merge". Use --docs on "/hv-docs", "update docs"; auto-invoked post-cycle when docs/ exists.

0
installs
▌
Hv Work · l4ci
Orchestrator-driven parallel implementation — plans tasks, dispatches workers, verifies, commits atomically per task. Workers run as in-process subagents (default) or, under work.dispatch=tmux, as separate Claude Code sessions in their own worktrees that open PRs behind a merge gate. Supports branch or worktree isolation and direct merge or PR. Use when items already exist in BACKLOG.md and need implementation ("implement [B07]", "build these"); for an item not yet captured use /hv-go.

0
installs
▌
Hv Debug · l4ci
Systematic root-cause investigation for a bug — reads the TODO entry + detail file, consults KNOWLEDGE.md, reproduces, hypothesizes, verifies, fixes with one atomic commit, and nudges /hv-learn. Use on "debug [B07]", "why is X broken", "investigate the crash", when a bug needs a proper cycle rather than a /hv-go shot.

0
installs
▌
Hv Learn · l4ci bundle
Extract durable session learnings (gotchas, conventions, constraints) into .hv/KNOWLEDGE.md grouped by topic, and update the CLAUDE.md topic index. Use at end of a session that surfaced reusable knowledge, after a correction-rich debugging arc, or on "save what we learned", "capture this learning", "/hv-learn". Opus verification is on by default via learn.verify in config.json; set to false for fast/cheap mode.

0
installs
▌
Hv Pause · l4ci
Gracefully pause mid-session — writes a handoff note (current hypothesis, next planned step, mid-edit files, uncommitted work strategy) to .hv/handoff/<branch>.md so /hv-next in a fresh session can pick up with full context, not just git state. Use when the session is approaching a context limit, you need to hand off, or you want to stop a long /hv-work cycle cleanly.

0
installs
▌
Hv Spike · l4ci
Throwaway feasibility experiment on a dedicated git branch — answers a specific question without polluting main or the backlog. Creates spike/<name> branch and .hv/spikes/<name>.md for question + findings + decision. Branch is never merged; only findings come back. Use when you need to try X before committing to it ("can we use SSE?", "does this library handle our scale?").

0
installs
▌
Hv Config · l4ci
**Print the banner below verbatim before any other action — skip if dispatched as a subagent.** See `references/banner-preamble.md`.

0
installs
▌
Hv Decide · l4ci
Capture a hard-boundary decision into .hv/DECISIONS.md — manually confirmed, never auto-invoked. Decisions differ from learnings in KNOWLEDGE.md by being active commitments with explicit forbids/permits. Use on "decide on X", "we're committing to X", "lock in the boundary that Y", or when a session has produced a constraint future work must respect. Accepts `--from-learning <topic>` to promote a hardened KNOWLEDGE.md learning into a decision, and `--from-spike <name>` to promote a `.hv/spikes/<name>.md` finding.

0
installs
▌
Hv Review · l4ci
Staff-engineer review of a feature branch before merge or PR — reads commits, diff, referenced item IDs, and matching KNOWLEDGE.md topics; dispatches an Opus reviewer that checks intent match, convention compliance, and quality. Returns PASS / CONCERNS / FAIL. Use on "review this", "check before I ship", "look over the branch", or implicitly from /hv-ship.

0
installs
▌
Hv Update · l4ci
Check for a newer hv-skills release on GitHub and tell the user how to update — detects install type (plugin, stow, repo clone), compares plugin.json version against the latest release, and prints the exact update command. Read-only; does not run the update itself. Use on "check for updates", "is hv-skills up to date", before long /hv-work sessions.

0
installs
▌
Hv Vision · l4ci
Brainstorm a project's vision and break it into milestones — Socratic discovery, web research, deliberate challenge, then write MILESTONES.md and per-milestone detail files. Handles fresh vision and editing/extending an existing one. Use on "let's plan", "what's the bigger picture", "create a roadmap", "brainstorm milestones".

0
installs
▌
Hv Capture · l4ci
**Print the banner below verbatim before any other action — skip if dispatched as a subagent.** See `references/banner-preamble.md`.

0
installs
▌
Hv Migrate · l4ci
**Print the banner below verbatim before any other action — skip if dispatched as a subagent.** See `references/banner-preamble.md`.

0
installs
▌
Hv Release · l4ci
Cut a release — walk the project's per-project release checklist (`.hv/RELEASE.md`) as a preflight gate, bump version (major/minor/patch), generate categorized release notes from commits since the last tag, prepend a section to CHANGELOG.md, create an annotated git tag, push, publish a release on GitHub or GitLab if origin is set, and offer to close any upstream issues still open for shipped items. Use on "release", "cut a release", "tag a release", "ship X.Y.Z".

0
installs
▌
Hv Refactor · l4ci
Run a full architectural refactor cycle — explores the codebase for friction, categorizes dependencies, designs competing approaches for structural changes, then fixes everything with parallel subagents. Use when you want to find and fix architectural issues.

0
installs
▌
Hv Brainstorm · l4ci
Per-item design exploration before /hv-plan — Socratic discovery, 2-3 approaches with tradeoffs, sectioned design with per-section approval, writes .hv/designs/<ID>.md, hands off to /hv-plan. Use when a Major feature or P0 bug needs design negotiation before implementation planning.

0
installs
▌
Pestel Analysis · l4ci bundle
Use when the user wants to scan the macro-environment around a company, industry, market, or decision using PESTEL (Political, Economic, Social, Technological, Environmental, Legal). Fans out six parallel analyst subagents (one per factor) to identify and assess the external forces, then prioritizes them by impact and certainty and draws implications in a detailed markdown report. Triggers include "PESTEL", "PEST analysis", "PESTLE", "macro-environment", "external factors", "what trends affect this market".

0
installs
▌
Six Sigma Dmaic · l4ci bundle
Use when the user wants to improve an existing process by reducing defects or variation using Six Sigma DMAIC (Define, Measure, Analyze, Improve, Control). Guides the five phases with gate checks, uses parallel root-cause hypotheses in Analyze, insists on verifying causes against data, and maintains a DMAIC project document. Triggers include "Six Sigma", "DMAIC", "reduce defects", "process improvement", "root cause analysis", "reduce variation".

0
installs
▌
Strategy Kernel · l4ci bundle
Use when the user wants to build or test a real strategy for an organization, unit, or initiative, or to check whether an existing "strategy" is actually one. Captures the challenge, fans out competing diagnostician subagents to name the crux from different angles in parallel, then synthesizes the sharpest diagnosis into a kernel (diagnosis, guiding policy, coherent action) and audits the result against Rumelt's four hallmarks of bad strategy in a detailed markdown report. Triggers include "strategy kernel", "good strategy bad strategy", "Rumelt", "what's our strategy", "diagnosis guiding policy", "is this a real strategy".

0
installs
▌
Fermi Estimation · l4ci bundle
Use when the user needs a defensible quantitative estimate of something with no data at hand, and wants a reasoned order-of-magnitude answer rather than a blind guess or a refusal. Runs Fermi estimation: defines the target quantity precisely, decomposes it in parallel into a chain of sub-factors each estimable to within an order of magnitude, estimates each factor as a range with its basis, multiplies the chain and propagates the uncertainty, then cross-checks the result against independent decompositions and known bounds and names the factor that dominates the error. Triggers include "Fermi estimate", "back of the envelope", "order of magnitude", "ballpark", "how many / how much / how big roughly", "estimate the market size", "we don't have data but need a number".

0
installs
▌
First Principles · l4ci bundle
Use when the user wants to reason a problem up from fundamentals instead of by analogy to how it is already done, challenge the assumptions baked into a conventional approach, or rebuild a solution from the ground up. Frames the received approach and the goal it serves, fans out parallel subagents that tear down inherited assumptions and establish what is actually bedrock, then reconstructs a solution from the surviving fundamentals and contrasts it with convention in a detailed markdown report. Triggers include "first principles", "first-principles thinking", "reason from scratch", "challenge assumptions", "why do we do it this way", "from the ground up".

0
installs
▌
Negotiation Prep · l4ci bundle
Use when the user is preparing for a negotiation (salary, deal, partnership, vendor, dispute settlement) and wants to go in ready rather than improvising. Fans out five parallel analyst subagents over the structure of principled, interest-based negotiation (Fisher and Ury, plus BATNA and ZOPA): your interests, their likely interests, your BATNA and walk-away, their likely BATNA and walk-away, and options for mutual gain with the objective criteria to invoke. Each marks every claim as fact or assumption with a confidence. A synthesis pass maps the zone of possible agreement, sets your target and walk-away, sequences the moves, and names the assumptions worth testing, into a detailed markdown report. Triggers include "prepare for a negotiation", "negotiation prep", "BATNA", "getting to yes", "salary negotiation", "how should I negotiate".

0
installs
▌
Scenario Planning · l4ci bundle
Use when the user wants scenario planning for an uncertain future: framing a focal question, finding critical uncertainties, building a 2x2 of plausible futures, and deriving strategy that holds across them. Gathers driving forces and selects the two critical uncertainties as axes, then fans out four scenario-builder subagents in parallel (one per quadrant) to develop named narratives, and synthesizes robust versus contingent strategy with the signposts to monitor. Triggers include "scenario planning", "scenario analysis", "2x2 scenarios", "critical uncertainties", "what if the future", "plan for uncertainty".

0
installs
▌
Six Thinking Hats · l4ci bundle
Use when the user wants to examine an idea, plan, or decision from every angle, run a structured deliberation, or break an adversarial deadlock using Edward de Bono's Six Thinking Hats. Defines a focus question with the Blue hat, fans out five parallel subagents that each look at that question in one strict mode (White facts, Red feelings, Black caution, Yellow benefits, Green creativity), then synthesizes them into a Blue-hat conclusion with concrete actions, the emotional read, and which risks must be mitigated versus which ideas neutralize them. Triggers include "six thinking hats", "de Bono", "look at this from all angles", "parallel thinking", "structured deliberation".

0
installs
▌
Balanced Scorecard · l4ci bundle
Use when the user wants to translate a strategy into a balanced set of objectives and measures using the Balanced Scorecard, or asks to build KPIs and a strategy map from a stated strategy or vision. Fans out four parallel analyst subagents (one per perspective: Financial, Customer, Internal Process, Learning & Growth), each deriving objectives, measures, targets, and initiatives from the strategy, then synthesizes a strategy map linking them by cause and effect and prunes to the vital few measures, all into a detailed markdown report. Triggers include "balanced scorecard", "BSC", "Kaplan Norton", "strategy map", "KPIs from strategy", "performance measurement framework".

0
installs
▌
Mece Decomposition · l4ci bundle
Use when the user wants to break a problem, question, metric, or topic into a clean structure with no overlaps and no gaps, or build an issue tree / logic tree. Generates competing MECE decompositions in parallel, selects the sharpest cut, builds the tree, then audits it for mutual exclusivity and collective exhaustiveness with parallel checkers. Triggers include "MECE", "mutually exclusive collectively exhaustive", "issue tree", "logic tree", "break this down", "structure this problem", "decompose".

0
installs
▌
Blue Ocean Strategy · l4ci bundle
Use when the user wants a Blue Ocean Strategy analysis of a business or product, or asks how to stop competing on the same factors as everyone else and create uncontested market space. Maps the industry's strategy canvas, then fans out four parallel subagents (eliminate, reduce, raise, create) to build a new value curve through value innovation, then synthesizes the blue-ocean move and its risks into a detailed markdown report. Triggers include "Blue Ocean", "value innovation", "ERRC", "four actions framework", "strategy canvas", "uncontested market", "stop competing on the same factors".

0
installs
▌
Porters Five Forces · l4ci bundle
Use when the user wants a Porter's Five Forces analysis of an industry or market, or asks to assess an industry's competitive structure, attractiveness, or profit potential. Fans out five parallel analyst subagents (one per force), each scoring its force against the standard determinants with real evidence, then synthesizes overall industry attractiveness and strategic implications into a detailed markdown report. Triggers include "Five Forces", "Porter analysis", "how attractive is this industry", "competitive structure of X".

0
installs
▌
Rice Prioritization · l4ci bundle
Use when the user wants to rank a backlog of product initiatives or features by expected value per unit of effort using Intercom's RICE model. Calibrates the goal, the Reach time window, the Impact scale, the Confidence levels, and the Effort unit first, then estimates each initiative in parallel, one subagent per initiative, before computing RICE = (Reach × Impact × Confidence) / Effort, ranking, running a sensitivity check on Confidence and Effort, and recommending a roadmap order in a markdown report. Triggers include "RICE", "RICE score", "RICE prioritization", "prioritize the backlog", "rank these features", "what should we build first", "score our roadmap", "reach impact confidence effort".

0
installs
▌
Root Cause Analysis · l4ci bundle
Use when a defect, failure, incident, or recurring problem has an unclear cause and the user wants to find and fix what actually causes it rather than patch the symptom. Combines the Ishikawa fishbone (cause-and-effect diagram) with the 5 Whys. Fans out parallel finder subagents, one per cause category (the 6 Ms by default), each brainstorming candidate causes for the category with reasoning and evidence; then drills the strongest candidates with iterative why-chains to reach verified root causes, separates root from contributing causes, and recommends countermeasures that remove the roots. Triggers include "root cause analysis", "RCA", "fishbone", "Ishikawa", "cause and effect", "5 whys", "why does this keep happening".

0
installs
▌
Cognitive Bias Audit · l4ci bundle
Use when the user wants to audit a decision, plan, forecast, or analysis for cognitive biases before committing to it, or to stress-test where reasoning might be systematically distorted. Fans out five parallel hunter subagents, one per bias family, each finding where THIS decision is exposed with evidence from the actual reasoning, then ranks the live biases by how much they threaten the call, names the one or two most dangerous, and prescribes specific debiasing moves plus a corrected read in a detailed markdown report. Triggers include "cognitive bias", "audit this decision for bias", "what biases are at play", "debias", "am I fooling myself", "stress-test my reasoning".

0
installs
▌
Force Field Analysis · l4ci bundle
Use when the user wants a force field analysis of a proposed change, decision, or goal, or asks what is driving and what is holding a change back, or whether a change is feasible as things stand. Fans out finder subagents in parallel that hunt the driving forces and the restraining forces across people, organizational, technical, and external lenses and score each by strength, then synthesizes the scored force field, the net read, and the highest-leverage moves (favouring the weakening of restrainers) into a detailed markdown report. Triggers include "force field analysis", "Lewin", "driving and restraining forces", "what's holding this change back", "forces for and against", "change readiness".

0
installs
▌
Psychological Safety · l4ci bundle
Use when the user wants to diagnose a team's psychological safety and prescribe how to improve it, or asks why people are not speaking up, why mistakes get hidden, or why learning has stalled. Fans out parallel assessor subagents across the dimensions of the climate (voice, response to mistakes, help-seeking, inclusion of difference, risk-taking and challenge), each scoring the climate against Amy Edmondson's behavioral markers with evidence and confidence, then places the team on the safety-by-accountability 2x2, names the weakest dimensions and the behaviors driving them, and prescribes leader and team interventions in a detailed markdown report. Triggers include "psychological safety", "people aren't speaking up", "mistakes get hidden", "Edmondson", "safe to take risks", "fearless team".

0
installs
▌
Stakeholder Analysis · l4ci bundle
Use when the user wants a stakeholder analysis or stakeholder map of a project, change, or decision, or asks who they need on board and how to engage them. Identifies the stakeholders, then fans out one analyst subagent per stakeholder in parallel to assess power, interest, current stance, interests and fears, and how to engage them, then synthesizes a power-interest grid, a per-quadrant engagement plan, the supporter coalition, the set of blockers, and the highest-leverage relationships to shift, in a detailed markdown report. Triggers include "stakeholder analysis", "stakeholder mapping", "power-interest grid", "power/interest matrix", "Mendelow", "stakeholder management", "who do we need on board".

0
installs
▌
Value Chain Analysis · l4ci bundle
Use when the user wants to analyze how a company creates value and where its competitive advantage lies, using Porter's Value Chain (inbound logistics, operations, outbound logistics, marketing and sales, service, plus firm infrastructure, HR, technology development, procurement). Fans out parallel analyst subagents per activity to assess cost and value contribution versus competitors, then synthesizes the sources of advantage, weak links, and linkages in a detailed markdown report. Triggers include "value chain", "value chain analysis", "where do we create value", "cost and differentiation drivers", "Porter value chain".

0
installs
▌
Business Model Canvas · l4ci bundle
Use when the user wants a Business Model Canvas of a company, product, or venture, or asks to map out how a business creates, delivers, and captures value. Fans out nine parallel analyst subagents (one per building block), each describing its block for the specific business with evidence and flagging assumptions versus facts, then synthesizes whether the blocks cohere, where the model is strongest and weakest, and which assumptions are riskiest into a detailed markdown report. Triggers include "Business Model Canvas", "BMC", "map the business model", "Osterwalder canvas", "nine building blocks".

0
installs
▌
Key Assumptions Check · l4ci bundle
Use when an analysis, plan, estimate, or forecast rests on things being taken for granted, and the user wants to find the load-bearing assumptions before one of them breaks. Runs the Key Assumptions Check (KAC), a core structured analytic technique: surfaces the full set of assumptions in parallel from several stances, restates each as an explicit testable proposition, stress-tests each one for confidence and the conditions under which it fails, classifies them as solid, caveated, or unsupported, and names the few linchpin assumptions that would collapse the conclusion if wrong. Triggers include "key assumptions check", "what are we assuming", "what is this resting on", "check our assumptions", "what if we're wrong about", "pressure-test this plan's premises".

0
installs
▌
Decision Tree Analysis · l4ci bundle
Use when the user faces a decision with uncertain outcomes and wants the choice that maximizes expected value, or asks to map options and chance events into a decision tree and solve it. Frames the root decision, its later choices, and the chance events into one tree, fans out parallel subagents to estimate each branch's probabilities and payoffs, then folds back (expected value at chance nodes, best choice at decision nodes) to mark the optimal path, with break-even and value-of-information analysis, in a detailed markdown report. Triggers include "decision tree", "expected value", "decision analysis", "EV", "fold back", "decision under uncertainty".

0
installs
▌
Ocean Personality Test · l4ci bundle
Use when the user wants to take a Big Five (OCEAN) personality test or asks to assess their personality across Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. Administers the public-domain 50-item IPIP questionnaire conversationally, scores it, and writes a detailed markdown report. Triggers include "OCEAN test", "Big Five", "personality assessment", "what's my personality type".

0
installs
▌
Hexaco Personality Test · l4ci bundle
Use when the user wants a HEXACO personality assessment, or a Big Five test that also measures Honesty-Humility. Administers the public-domain 240-item IPIP-HEXACO questionnaire conversationally across six factors (Honesty-Humility, Emotionality, eXtraversion, Agreeableness, Conscientiousness, Openness) and their 24 facets, scores it, and writes a detailed markdown report. Triggers include "HEXACO test", "HEXACO personality", "Honesty-Humility", "Big Five plus honesty", "six-factor personality assessment".

0
installs
▌
Tosca Problem Definition · l4ci bundle
Use when the user has a fuzzy or broad problem and needs to sharpen it into a crisp, solvable problem statement before analyzing or solving it. Walks through the TOSCA framework (Trouble, Owner, Success criteria, Constraints, Actors) as a guided interview, challenges weak answers, stress-tests the framing with parallel critic subagents, and writes a problem-definition brief. Triggers include "TOSCA", "define the problem", "frame this problem", "problem statement", "I'm not sure what the real problem is", "Bulletproof Problem Solving".

0
installs
▌
Value Proposition Canvas · l4ci bundle
Use when the user wants a Value Proposition Canvas for an offering and a customer segment, or asks to test whether a product fits what a customer actually needs. Fans out six parallel analyst subagents, three describing and ranking the Customer Profile (jobs, pains, gains) and three describing the Value Map (products and services, pain relievers, gain creators), each marking claims as fact or assumption, then ranks the customer side and assesses fit: which top jobs, pains, and gains the value map addresses, which it misses, and which relievers and creators chase things the customer does not care about. Produces a detailed markdown report. Triggers include "Value Proposition Canvas", "VPC", "value proposition design", "problem-solution fit", "does this fit the customer".

0
installs
▌
Weighted Decision Matrix · l4ci bundle
Use when the user wants to choose among several options against multiple weighted criteria with a transparent, defensible score (the weighted scoring model or Pugh matrix). Calibrates the criteria, their weights, and the scoring scale first, then scores each option in parallel, one subagent per option, before computing weighted totals, ranking, and running a sensitivity check in a markdown report. Triggers include "decision matrix", "weighted scoring", "Pugh matrix", "compare options against criteria", "which option should we choose", "weighted decision model", "selection matrix".

0
installs
▌
Impact Feasibility Matrix · l4ci bundle
Use when the user has a list of initiatives, ideas, features, or projects and wants to prioritize them by impact and feasibility (the impact-effort matrix), sorting into quick wins, major projects, fill-ins, and thankless tasks. Defines the axes, scores each option in parallel, places them in quadrants, and recommends a sequenced plan in a markdown report. Triggers include "impact vs feasibility", "impact-effort matrix", "prioritize these", "what should we do first", "quick wins", "prioritization matrix".

0
installs
▌
Self Determination Theory · l4ci bundle
Use when the user wants to understand why a person, role, or team has gone disengaged, demotivated, resistant, or burnt out, and what would actually re-engage them, including assessing their own motivation. Runs Deci and Ryan's Self-Determination Theory by fanning out three parallel analyst subagents, one per basic psychological need (Autonomy, Competence, Relatedness), each scoring both satisfaction and frustration for its need with evidence and how much it bears on the problem, then names the binding need, places motivation on the controlled-to-autonomous continuum, and prescribes targeted need-supportive moves in a detailed markdown report. Guards against the reflex of blaming generic "low motivation" when one specific need is being thwarted. Triggers include "self-determination theory", "SDT", "autonomy competence relatedness", "intrinsic motivation", "why is the team disengaged", "basic psychological needs".

0
installs
▌
Digital Maturity Assessment · l4ci bundle
Use when the user wants to assess an organization's digital maturity across strategy, customer experience, technology, data, operations, people and culture, and innovation, scoring each on a five-level scale and producing a gap analysis and roadmap. Fans out parallel assessor subagents per dimension, then synthesizes the maturity profile, the binding gaps, and a sequenced roadmap in a detailed markdown report. Triggers include "digital maturity", "digital maturity assessment", "how digitally mature are we", "digital transformation readiness", "maturity model".

0
installs
▌
Five Dysfunctions Of A Team · l4ci bundle
Use when the user wants to diagnose why a team is underperforming, conflict-avoidant, political, or not delivering, using Patrick Lencioni's Five Dysfunctions model. Fans out five parallel analyst subagents, one per layer of the pyramid (Absence of Trust, Fear of Conflict, Lack of Commitment, Avoidance of Accountability, Inattention to Results), each assessing the team against that layer's tells with behavioral evidence, then synthesizes by locating the lowest broken layer, tracing how a cracked base surfaces as higher-layer symptoms, and prescribing interventions from the base upward into a detailed markdown report. Triggers include "five dysfunctions", "Lencioni", "why is my team dysfunctional", "team isn't delivering", "diagnose this team".

0
installs
▌
Reference Class Forecasting · l4ci bundle
Use when the user must forecast a duration, cost, success rate, or outcome and is tempted to estimate from the specifics of their own case, which systematically underestimates and over-optimizes. Runs reference-class forecasting (the outside view): defines the prediction, builds in parallel a class of similar past cases, constructs the empirical distribution of how that class actually turned out, anchors the forecast on that base rate, then adjusts for the case's true distinctiveness under adversarial checks for optimism and regression to the mean. Triggers include "reference class forecasting", "outside view", "base rate", "planning fallacy", "how long will this really take", "are we being too optimistic", "how do projects like this usually go".

0
installs
▌
Analysis Of Competing Hypotheses · l4ci bundle
Use when the user must decide which of several explanations is true and wants to avoid latching onto the first plausible story. Runs Heuer's Analysis of Competing Hypotheses (ACH): lays out all plausible hypotheses at once, scores every piece of evidence against each one in parallel by working to disprove rather than confirm, then ranks hypotheses by fewest inconsistencies, stress-tests the linchpin evidence for fragility and deception, and reports relative likelihoods with the indicators that would change the answer. Triggers include "ACH", "competing hypotheses", "which explanation is most likely", "what's really going on here", "rule out the alternatives".

0
installs
▌
Okr · l4ci bundle
Use when the user wants to turn strategy into measurable goals using OKRs (Objectives and Key Results), the goal-setting method from Andy Grove at Intel and popularized by John Doerr in Measure What Matters. Guides a drafting cycle: clarify a qualitative objective, draft 3-5 measurable key results, stress-test the key results with parallel critics, set ambition and cadence, and check alignment. Maintains an OKR document. Triggers include "OKR", "OKRs", "objectives and key results", "set quarterly goals", "Measure What Matters", "draft our objectives".

0
installs
▌
Fmea · l4ci bundle
Use when the user wants to systematically anticipate how a process, product, or design can fail before launching or changing it (Failure Mode and Effects Analysis). Scopes the system and breaks it into functions or steps, then dispatches one analyst per function in parallel to list failure modes with effects, causes, controls, and Severity/Occurrence/Detection scores, before a synthesis pass computes the Risk Priority Number, ranks the modes, applies an action threshold plus a high-severity override, and recommends actions that reduce S, O, or D. Triggers include "FMEA", "failure mode and effects analysis", "what could go wrong with this process", "risk priority number", "RPN", "DFMEA", "PFMEA", "design failure analysis".

0
installs
▌
Adkar · l4ci bundle
Use when the user wants an ADKAR analysis of a change, asks why a change is not sticking or not being adopted, or wants to diagnose the people side of a change initiative. Identifies the affected groups, then fans out five parallel subagents (one per element: Awareness, Desire, Knowledge, Ability, Reinforcement), each rating the current state per group with evidence, then synthesizes the barrier point for each group and designs sequenced interventions into a detailed markdown report. Triggers include "ADKAR", "Prosci", "individual change model", "change adoption", "why is this change not sticking", "people side of change".

0
installs
▌
Com B · l4ci bundle
Use when the user wants to understand why a target behaviour is or is not happening and what would actually change it, product adoption, process compliance, safety behaviour, habit formation, organizational change. Fans out six parallel analyst subagents, one per COM-B sub-component (Physical and Psychological Capability, Physical and Social Opportunity, Reflective and Automatic Motivation), each judging whether its component is sufficient or a barrier with evidence, severity, and confidence, then synthesizes the binding constraint, maps it to the right intervention functions of the Behaviour Change Wheel, and designs targeted interventions. Guards against the default error of assuming the problem is motivation when it is opportunity or capability. Triggers include "COM-B", "Behaviour Change Wheel", "why won't people do X", "behaviour change", "drive adoption", "improve compliance".

0
installs
▌
Scarf · l4ci bundle
Use when the user is rolling out a change, giving feedback, designing a communication, planning a reorganization, or making a contentious decision and wants to see where people will feel socially threatened and how to lower it. Runs David Rock's SCARF model by fanning out five parallel analyst subagents, one per domain (Status, Certainty, Autonomy, Relatedness, Fairness), each assessing the threat and reward the situation creates in its domain with evidence and a severity, then synthesizes the biggest threats, the domains most at risk, and specific moves that lower threat and raise reward into a detailed markdown report. Triggers include "SCARF", "SCARF model", "social threat", "why are people resisting this change", "David Rock SCARF".

0
installs
▌
Cynefin · l4ci bundle
Use when the user faces a hard, messy, or stuck problem and needs to pick the right approach before reaching for any other tool, or when plans keep failing because a complex problem is being handled as if it were merely complicated. Surfaces the constituent issues of a situation, then fans out parallel classifiers that place each issue into one of Cynefin's domains (Clear, Complicated, Complex, Chaotic, or Disorder) with evidence and the matching action model, then synthesizes the portfolio across the domains, flags any issue on the Clear-Chaotic cliff or stuck in Disorder, and recommends a domain-appropriate approach and which other framework fits each. Triggers include "Cynefin", "what kind of problem is this", "complex vs complicated", "why do our plans keep failing", "Snowden sense-making".

0
installs
▌
Tuckman · l4ci bundle
Use when the user wants to diagnose a team's stage of development and what it needs to advance, or asks why a team is stuck, conflicted, or not yet performing. Fans out five parallel assessor subagents (one per stage: Forming, Storming, Norming, Performing, Adjourning), each scoring how well the team's observable behaviors match that stage with evidence and noting regression signals, then synthesizes the current stage, the matching leadership focus, the concrete moves to advance, and what is blocking the transition into a detailed markdown report. Triggers include "Tuckman", "stages of team development", "forming storming norming performing", "what stage is my team at", "why is my team stuck".

0
installs
▌
Inversion · l4ci bundle
Use when the user wants to attack a goal or problem backward instead of forward, asking what would guarantee failure or the opposite outcome so those paths can be avoided. Fans out parallel subagents that each generate ways to cause the worst result across a distinct lens, then ranks the failure paths, distills the absolute bright lines, and turns each into an avoid-rule or action in a markdown report. Triggers include "inversion", "invert the problem", "work backward", "how could this fail", "avoid stupidity", "Munger inversion".

0
installs
▌
Ooda Loop · l4ci bundle
Use when the user faces a fast-moving, uncertain situation and wants to run an OODA loop (Observe, Orient, Decide, Act), John Boyd's decision cycle. Guides a tight, repeating loop: observe what is actually happening, orient by breaking and rebuilding the mental model, decide the next move as a hypothesis, act small and fast, then loop. Keeps the focus on orientation and tempo, and maintains a loop log. Triggers include "OODA", "OODA loop", "observe orient decide act", "Boyd", "get inside their decision loop", "fast-moving decision".

0
installs
▌
Bcg Matrix · l4ci bundle
Use when the user wants to analyze a portfolio of business units or product lines with the BCG Growth-Share Matrix, classifying each into Stars, Cash Cows, Question Marks, or Dogs and recommending where to invest, hold, harvest, or divest. Fans out one analyst subagent per unit in parallel to place it on market growth and relative market share, then synthesizes portfolio balance, cash flow, and strategy into a detailed markdown report. Triggers include "BCG matrix", "growth-share matrix", "Stars and Cash Cows", "portfolio analysis", "which products to invest in or kill".

0
installs
▌
Kano Model · l4ci bundle
Use when the user wants to decide which product features to build, prioritize, cut, or how to position them, or asks how features drive customer satisfaction. Fans out parallel analyst subagents (one per candidate feature) that reason through the functional and dysfunctional customer responses for a target segment, assign a Kano category (must-be, one-dimensional, attractive, indifferent, or reverse) with rationale, confidence, decay risk, and segment sensitivity, then synthesizes a feature set: confirm the must-bes are covered, pick the performance features to compete on, choose a few delighters, drop the indifferent, avoid the reverse, and sequence with a decay timeline into a detailed markdown report. Triggers include "Kano model", "Kano analysis", "must-be vs delighter", "classify these features", "delighters", "which features matter".

0
installs
▌
Pdca Cycle · l4ci bundle
Use when the user wants to run a lightweight continuous-improvement loop using PDCA (Plan, Do, Check, Act), the Deming cycle. Guides a small, fast cycle: plan a change with an explicit prediction, try it at small scale, check results against the prediction, and act by adopting, adjusting, or abandoning, then loop. Maintains a cycle log. Triggers include "PDCA", "Deming cycle", "plan do check act", "continuous improvement", "Shewhart cycle", "kaizen loop".

0
installs
▌
Pre Mortem · l4ci bundle
Use when the user wants to stress-test a plan, proposal, PRD, strategy, or decision before committing to it. Runs a prospective-hindsight pre-mortem by fanning out independent failure-finder subagents across distinct risk lenses, deduplicating and scoring the risks by likelihood and impact, then designing mitigations for the worst ones. Triggers include "pre-mortem", "red-team this plan", "what could go wrong", "stress-test this", "poke holes in this proposal".

0
installs
▌
Mckinsey 7s · l4ci bundle
Use when the user wants to assess organizational alignment or effectiveness, diagnose why an organization underperforms, plan a major change, or integrate after a merger, using the McKinsey 7-S framework (Strategy, Structure, Systems, Shared Values, Skills, Style, Staff). Fans out seven parallel analyst subagents (one per element), then runs an alignment analysis across them to find misalignments and recommend fixes, in a detailed markdown report. Triggers include "7-S", "7S framework", "McKinsey 7-S", "organizational alignment", "why is this org not working".

0
installs
▌
Hoshin Kanri · l4ci bundle
Use when the user wants to deploy a strategy into aligned, measurable action using Hoshin Kanri (policy deployment, strategy deployment), or asks to build an X-matrix, cascade breakthrough objectives, or align daily work with strategy. Establishes the vital few breakthrough objectives and their annual objectives, fans out one strategist subagent per annual objective to develop improvement priorities, targets, and owners, then synthesizes the X-matrix, the correlations, the alignment check, and the catchball and review cadence into a detailed markdown report. Triggers include "Hoshin Kanri", "policy deployment", "strategy deployment", "X-matrix", "hoshin planning", "catchball", "cascade strategy to execution".

0
installs
▌
Lean Startup · l4ci bundle
Use when the user wants to test a startup, product, or business idea under uncertainty using the Lean Startup method (Build-Measure-Learn, MVP, validated learning, pivot or persevere). Surfaces the leap-of-faith assumptions, ranks them by risk with parallel analysis, designs the smallest experiment with a pre-committed metric, and runs the loop toward a pivot-or-persevere decision. Triggers include "lean startup", "MVP", "build measure learn", "validate my idea", "value and growth hypothesis", "pivot or persevere".

0
installs
▌
Scqa Pyramid · l4ci bundle
Use when the user has a recommendation, findings, or decision to communicate and wants it structured top-down so the answer comes first. Generates competing SCQA framings in parallel, selects the sharpest, builds the supporting pyramid, then audits the logic and the key line with parallel checkers. Triggers include "Pyramid Principle", "SCQA", "Minto", "structure my argument", "executive summary", "answer first", "storyline", "structure this recommendation".

0
installs
▌
Ansoff Matrix · l4ci bundle
Use when the user wants to explore growth strategies for a company or product using the Ansoff Matrix (Market Penetration, Market Development, Product Development, Diversification). Fans out four parallel strategist subagents, one per quadrant, to generate concrete growth options with risk and capability fit, then synthesizes a prioritized growth path in a detailed markdown report. Triggers include "Ansoff matrix", "growth strategy", "how should we grow", "market penetration vs diversification", "product/market growth".

0
installs
▌
Kotter Change · l4ci bundle
Use when the user wants to lead an organizational change using Kotter's 8-step model (urgency, coalition, vision, communication, removing barriers, short-term wins, sustaining acceleration, anchoring in culture). Facilitates the eight sequential steps with a gate check per step, uses parallel subagents within a step where useful, and maintains a change plan document. Triggers include "Kotter", "8-step change", "Leading Change", "change management", "drive organizational change", "manage a transformation".

0
installs
▌
Swot Analysis · l4ci bundle
Use when the user wants a SWOT analysis of a company, product, project, team, or decision, or asks to assess strengths, weaknesses, opportunities, and threats. Fans out four parallel analyst subagents (one per quadrant), grounds each factor in evidence and prioritizes it, then crosses the quadrants into a TOWS strategy matrix and a ranked set of strategic options in a detailed markdown report. Triggers include "SWOT", "SWOT analysis", "strengths and weaknesses", "TOWS", "analyze our position".

0
installs
▌
Vrio Analysis · l4ci bundle
Use when the user wants a VRIO analysis of a firm's resources and capabilities, or asks whether a resource is a source of sustained competitive advantage. Optionally surfaces candidate resources first, then fans out one analyst subagent per resource to run the four VRIO gates (Valuable, Rare, Costly to Imitate, Organized) with evidence and assign a competitive implication, then synthesizes the strategic core and fixable gaps into a detailed markdown report. Triggers include "VRIO", "VRIN", "resource-based view", "is this a sustainable advantage", "test our core competencies", "RBV".

0
installs
▌
Storm Research · l4ci bundle
Use when the user wants deep, PhD-level research on a topic. Runs a STORM-style multi-perspective investigation by fanning out parallel expert subagents (each doing its own retrieval), mapping where they contradict, synthesizing a CEO-grade briefing, then peer-reviewing it with a panel of independent critics that assign confidence scores and name the gaps.

0
installs
▌
Thomas Kilmann · l4ci bundle
Use when the user has a specific conflict, disagreement, or dispute to navigate and needs to decide how to handle it. Diagnoses the situation along assertiveness and cooperativeness, then fans out five parallel analyst subagents (one per conflict mode) to score how well each fits this situation, and synthesizes a primary mode and fallback with concrete words and actions, flagging when the user's habitual default is mismatched. Triggers include "Thomas-Kilmann", "TKI", "conflict mode", "how should I handle this conflict", "competing collaborating compromising avoiding accommodating".

0
installs
▌
Three Horizons · l4ci bundle
Use when the user wants to assess or plan growth and innovation across time using McKinsey's Three Horizons model (Horizon 1 core, Horizon 2 emerging, Horizon 3 options). Fans out three parallel analyst subagents (one per horizon) to place and assess initiatives, then synthesizes portfolio balance, pipeline gaps, and how each horizon should be funded and measured, in a detailed markdown report. Triggers include "three horizons", "3 horizons", "horizon 1 2 3", "growth horizons", "innovation portfolio", "balance core and future".

0
installs
▌
Concise Writing · l4ci bundle
Use when the user wants to write or edit text so it is only as long as it needs to be and carries no signs of AI writing. Anchors to the purpose and reader, then runs the text down a cut ladder (delete whole units before trimming words), scans it against the compressed catalog of AI tells, and reads it aloud, looping draft to audit to final. Guards against over-trimming so the floor stays meaning, not word count. Triggers include "tighten this", "make it shorter", "cut the fluff", "less verbose", "trim this", "de-slop", "this sounds AI-written", "write a concise", "edit for length".

0
installs
▌
Design Thinking · l4ci bundle
Use when the user wants to run a human-centered innovation process to design a product, service, feature, or experience, using Design Thinking (Empathize, Define, Ideate, Prototype, Test). Facilitates the five modes as an iterative loop, using parallel idea generation during Ideate, and keeps a living design document. Triggers include "design thinking", "human-centered design", "d.school process", "empathize define ideate", "How Might We", "design a solution for users".

0
installs
▌
Jobs To Be Done · l4ci bundle
Use when the user wants to understand why customers hire a product, shape or reposition an offering around real customer motivation, or decide what to build based on the progress customers are trying to make. Defines the customer and the struggling moment, then fans out parallel analyst subagents over the functional job, the emotional and social job, the desired outcomes, the competing solutions and nonconsumption, and the four forces of progress, and synthesizes a job story, an opportunity-scored ranking of outcomes, and implications for the offering into a detailed markdown report. Triggers include "jobs to be done", "JTBD", "what job is the customer hiring this for", "why do customers switch", "outcome-driven innovation".

0
installs

81 published skills