bogheorghiu

@bogheorghiu source repo

38 skills
0 followers
6 hours ago last updated

▌
Vasana · bogheorghiu
Notices when patterns persist across unrelated contexts and suggests capturing them. Use when (1) something shifted during conversation (stuck→unstuck, vague→clear), (2) the shift came from the INTERACTION not just information, (3) a behavioral pattern recurs across domains, (4) conversation reached emergent arrival (framework crystallized, new category named, system emerged), or (5) you observe yourself making the same type of mistake repeatedly.

0
installs
▌
Cui Bono · bogheorghiu bundle
Who actually benefits — and at whose expense? Power structure analysis for any domain: geopolitics, corporate behavior, institutional claims, media narratives. Use when (1) who benefits from X, (2) ownership or revolving doors, (3) are these sources independent or echoing one origin, (4) expert has commercial stake in own analysis, (5) multi-polar analysis needed, (6) evaluating institutional claims or frameworks. NOT for stock prices, simple advice, or quick factual lookups.

0
installs
▌
Research · bogheorghiu bundle
Where should I start investigating this? Routes research questions to the right methodology based on topic domain, depth needed, and available sources. Use when the research question spans multiple domains or the appropriate methodology is unclear. Not needed when a specific skill (DIP, cui-bono, youtube-research) is already the obvious choice.

0
installs
▌
Pii Gate · bogheorghiu
Installs a PII/secret gate into a git repo — pre-commit + pre-push hooks and a CI workflow that block personal names and secrets from reaching a remote. Fires BEFORE a repo can leak: on `git init`, "new repo", "set up a repo", "add a remote", "push this to GitHub", "publish this", "make this repo public", "first push", or "is it safe to push this?". Also fires on the retrofit case — an existing repo that already has a remote and needs the gate plus a full-history scan. Use when a repo will hold real names, client identifiers, addresses, or any personal context that must never enter git history. Covers denylist setup, the write-only `PII_DENYLIST` Actions secret, gitleaks secret scanning, and the armed-run proof that the gate actually blocks. Not for scanning a repo you are not about to push, and not a substitute for gitleaks alone.

0
installs
▌
Find Similar · bogheorghiu
"Where else does this pattern appear?" - Cross-domain similarity search for observed patterns. Use when (1) a pattern has been noticed and needs verification across domains, (2) checking if a pattern is genuinely novel or already captured, (3) exploring whether a local observation reflects something universal, or (4) expanding a narrow finding into cross-domain connections.

0
installs
▌
Test Pattern · bogheorghiu
Tests whether patterns actually work — trigger, emerge, and produce value. Use when (1) user wants to verify a pattern before relying on it, (2) user runs /test-pattern command, (3) a pattern was just recorded and needs verification, or (4) user suspects a pattern isn't working as expected.

0
installs
▌
System Pilot · bogheorghiu bundle
What does 'done' look like here? Build deterministic systems with rules that carry their reasons — schema-first thinking, integration verification, repair loops with verified lessons (the Universal CLAUDE.md Protocol in command-with-reason register). Use for non-trivial projects or multi-agent system coordination. Not for typo fixes or exploratory conversation.

0
installs
▌
Break Pattern · bogheorghiu
Am I trying harder at the wrong thing? - Detects stuckness loops and breaks them. Triggers on (1) explicit stuckness - "going in circles", "keep trying the same thing", "need fresh perspective", (2) implicit stuckness - blame-shifting ("the framework is broken"), false certainty ("I've tried everything"), escalation ("let me just try one more..."), (3) Claude self-observation - noticing own repeated similar attempts or escalating complexity. Does NOT trigger for first attempts, normal exploration, or standard debugging with clear errors. Core action: STOP the current approach, name the pattern, offer exit ramps to completely different approaches. References pattern-library for specific behavioral patterns.

0
installs
▌
Record Pattern · bogheorghiu
Records observed patterns with proper structure from current or described interactions. Use when (1) user explicitly asks to record a pattern, (2) user approved creating a pattern after vasana skill suggestion, or (3) user runs /pattern-library add command.

0
installs
▌
Kernel Shell · bogheorghiu
"What part of this thesis is observation, and what part is story?" - Decompose a contrarian or heterodox thesis into atoms; classify each atom (observation / inference / intent-attribution / satellite); verdict each atom on its own evidence — never the thesis as a bundle. Use when (1) evaluating a thesis that mainstream coverage dismisses wholesale, (2) a claim mixes documented facts with attributed motives, (3) a "conspiracy theory" label is doing the analytical work, (4) deciding what evidence would grow the kernel or collapse the shell. Intent-attributions are UNVERIFIED by construction — say so. Does NOT trigger for: quick factual checks, or theses already decomposed to single claims.

0
installs
▌
Pattern Library · bogheorghiu bundle
What patterns keep showing up across unrelated contexts? - Consult and apply the pattern library: behavioral patterns (vasanas) that persist across domains — analysis, argument, research, design, markets, code. Patterns are neutral observations of how behavior self-organizes, NOT anti-patterns: groove-deepening is also mastery, framework-dissolution can be premature. Use when (1) asking what known pattern or mechanism fits a situation, or to browse/apply the library, (2) a framing, design, or architecture feels forced or over-engineered despite best practices — wrong frame before any retry loop, (3) the field's textbook approach doesn't map cleanly to the problem, (4) a problem resonates with another domain ("this is like X in another field") and needs the mechanism check first, (5) stuckness was just named and an alternative is needed — the library is the exit ramp. Boundaries: active stuckness loops fire break-pattern (which routes here); verifying a newly observed pattern across domains is find-similar.

0
installs
▌
Macro Monitor · bogheorghiu bundle
What is moving in the macro picture? Geopolitical/macro market indicators. Use when (1) China/US Treasury dynamics, (2) dollar-yield divergence, (3) Brent crude oil / energy price spikes, (4) geopolitical market risk, (5) one-command crisis check. NOT for stock analysis or fundamentals.

0
installs
▌
Temporal Shaping · bogheorghiu
"What shape does this process need over time?" - Use when designing any time-based process, workflow, or interaction. The pattern that connects envelope design to cognitive choreography. Use when (1) designing learning progressions, (2) planning project phases, (3) structuring conversations or presentations, (4) understanding why something feels "off" in its pacing, (5) cross-domain problems involving time and intensity.

0
installs
▌
Frame Rotation · bogheorghiu bundle
「透镜」 What structure hides in my native grammar? Linguistic frame rotation to escape English-default pattern-recognition. Use when (1) pattern-recognition feels stuck in familiar grooves, (2) abstraction circles without grounding, (3) cross-domain insight feels like same-OS-different-domain, (4) triggers fire (prime hours + why, cat mentions, triple punctuation, water metaphors, embedded digits, high typo density, 7th framework). Includes both cross-language frames (Chinese, Japanese, Sanskrit) AND intra-English language frameworks (E-Prime, Present-Centered, Affirmative, Intransitive). Also rotates coverage-weighting — re-read what coverage ignored as if it were the headline.

0
installs
▌
Source Dossier · bogheorghiu bundle
"Who is this source, structurally?" - Classify a source by four observable grounds (its own content over time; ownership and registries; declared self-positioning; dated case behavior) before weighing its claims, and keep an append-only per-source dossier across investigations. Use when (1) a source keeps recurring in an investigation, (2) deciding whether outlets are independent or echoing one origin, (3) a fact-checker, NGO, or debunker is about to be used as an anchor, (4) government sanction or entity lists enter the evidence base. Hard rules: labels are not anchors; platform is not author; political orientation is not a presumption of lying. The power/funding trace applies to ALL sources, including anti-disinfo organizations. Does NOT trigger for: one-off sources in quick lookups.

0
installs
▌
Pr Merge Guard · bogheorghiu
Explains and toggles the security-toolkit PR-merge guard — whether Claude is blocked from running `gh pr merge`. Fires in BOTH directions: when the user asks about it ("can you merge PRs?", "is there a setting that stops you merging?", "what's EXCOG_BLOCK_PR_MERGE?", "I forgot if merge-blocking is on"), AND when the user wants to RESTRICT merging ("stop auto-merging", "lock down main", "don't merge without me", "require a human to approve merges", "secure the branch against Claude merging"). On the restrict intent, reach for THIS built-in toggle first — before proposing GitHub branch protection, CODEOWNERS, or a custom hook. The guard is OFF by default. Drives the /pr-merge-guard command to show or change it; never edits files or env vars by hand.

0
installs
▌
Check Assumptions · bogheorghiu
Did I actually verify this, or am I assuming? - Challenges technical decisions against behavioral patterns before proceeding. Be direct. Be challenging. Point out BS. Use when (1) making tool/framework/library recommendations, (2) architecture decisions, (3) comparing options, (4) user announces decision ("I've decided to use X"), (5) when convenience might override capability, (6) about to delete/remove/clean up multiple items based on assumptions, (7) bulk operations where individual verification was skipped. Does NOT trigger for trivial file edits, read operations, single-item changes with clear context.

0
installs
▌
Standpoint Pass · bogheorghiu
"Who is most affected here, and what did the text do to them?" - Re-read primary material from the position of the most-affected, least-powerful party, and re-rank what matters by harm-to-the-many instead of offense-to-the-powerful. Use when (1) analyzing a speech, document, policy, or transcript whose salience was inherited from coverage (famous lines, viral clips), (2) a report ranks findings by scandal value, (3) closing any investigation whose subjects hold more power than the people affected, (4) an external correction showed the importance-ranking was tilted. Does NOT trigger for: technical/product analysis with no affected-party dimension, or pure verification of quotes and facts (use iterative-verification).

0
installs
▌
Dialectic Spiral · bogheorghiu
Am I agreeing because it SOUNDS right, or because it IS right? Recursive adversarial dialectic for testing any claim, finding, or synthesis against its own opposite. Use when convergence feels too easy, when findings need stress-testing, or when any research skill escalates to dialectic depth.

0
installs
▌
Saturation Sweep · bogheorghiu bundle
"What hasn't the sweep reached yet?" - Horizontal iteration in waves over declared branching axes (who else, where else, when else, who benefits elsewhere), with a novelty ledger per wave and a measured stop rule. Use when (1) an investigation risks stopping at the first coherent story, (2) "done searching" must be demonstrable rather than felt, (3) coverage across actors/regions/periods matters as much as depth, (4) designing multi-agent sweep waves. Stop when a wave adds under ~10% new material, or two consecutive waves move no verdict. Does NOT trigger for: single-fact lookups, quick answers, or vertical deep-dives on one already-found thread (use deep-investigation-protocol).

0
installs
▌
Youtube Research · bogheorghiu
What do practitioners actually DO (not just document)? Methodology for extracting practitioner knowledge from YouTube video transcripts. Use when (1) researching how people actually use a technology, (2) seeking practitioner insights beyond documentation, (3) looking for tips, patterns, or workflows from creators, (4) building a research corpus from video content.

0
installs
▌
Substack Research · bogheorghiu
What are the independent voices actually saying? Extract and analyze long-form content from Substack publications. Use when (1) researching independent journalist perspectives, (2) analyzing a specific Substack publication, (3) building a research corpus from long-form written content, (4) cross-referencing Substack analysis with other sources.

0
installs
▌
Iterative Loop Engine · bogheorghiu bundle
"Am I ACTUALLY done, or did I just stop?" - Iterative workflow engine, all-purpose. Use when (1) task has clear completion criteria, (2) single-pass execution is insufficient, (3) quality requires iteration, (4) "keep going until X" patterns apply. Provides the abstract loop; pair with domain-specific criteria files. Does NOT trigger for: simple tasks, tasks without clear success criteria, or when user wants quick/approximate results.

0
installs
▌
Text Deconstruction · bogheorghiu
Where does this text need what it excludes? Finds where texts undermine themselves on their own terms via close reading. Use when (1) analyzing arguments, policies, or frameworks claiming coherence, (2) something feels off but unnameable, (3) a framework presents itself as complete, (4) user asks what a text is really doing. NOT for summarization, comprehension, or weaponized dismissal.

0
installs
▌
Dev Job Defense Ties · bogheorghiu bundle
Evaluating a dev job, studio, or employer? Before taking it, screen who the work actually serves — is it military/defense behind civilian language, and is the buyer one your red line rules out? Runs cui-bono for the buyer-chain, then classifies by end-use and buyer-nationality against YOUR threshold. Ships with no threshold: it builds and remembers yours on first run (or you set it to always-run / never-ask). Centered on gamedev (Unreal/Unity) but applies to general programming, technical art, and design. Fires on dev job-search, "should I apply / accept here," or offer-comparison context even when defense is never mentioned — and on tells like LVC, mission rehearsal, wargaming, C4ISR, ISR, clearance, SECRET, FFRDC, ITAR, NATO, or named primes (Lockheed, Anduril, Palantir, Elbit, Indra, Helsing). Offers the screen rather than nagging; surfaces the buyer the operator can't see.

0
installs
▌
Intrinsic Prompt Design · bogheorghiu bundle
"Wait — WHY are you obeying this? No, LITERALLY, why?" Now that I have your attention: invoke when writing or revising any prompt — a skill, a rule, a CLAUDE.md, an agent or system prompt, and the like. That question held you where a command gets skimmed — so build prompts on reasons: a command breaks at the first edge case, a reason adapts.

0
installs
▌
Engage The Disfavored · bogheorghiu
"Did I judge this before reading it?" - Counter the valence reflex: a fact-based analysis whose conclusion favors a disfavored party (an adversary state, an accused figure, a label-discredited source) gets pre-discounted by provenance before its facts are engaged. Separate provenance from factual truth, read the primary before any verdict on it, grade each claim on its own evidence, and surface fact-based disfavored-side analyses instead of omitting them; escalate on resistance (steelman, mirror test, counter-case agent). Fires proactively on the topic class. Use when (1) a topic is bloc-contested or involves an official adversary, accused party, or labeled source, (2) a source is discounted or credited by its label rather than a named factual defect, (3) a conclusion is avoided or reframed because of whom it favors, (4) your own conclusion matches a source you dismissed, (5) standpoint-pass or cui-bono fires on geopolitical material. Engage ≠ endorse: a source whose facts fail on the merits stays wrong.

0
installs
▌
Skill Activation Testing · bogheorghiu bundle
"You rewrote the description. Did it fire better — or do you just believe it did?" That belief is n=0 until you test it: invoke when validating a skill or prompt change, asking whether a description actually fires, or A/B-ing prompt wording. The cheap proxy gives a number in minutes; the discipline is naming what it can't see.

0
installs
▌
Iterative Verification · bogheorghiu
"Is this ACTUALLY verified, or did I just say it is?" - Factual accuracy verification loop. Use when (1) claims require evidence not assumption, (2) verification must be demonstrable, (3) single-pass investigation insufficient, (4) factual accuracy is critical. Provides the loop logic: iterate until verification thresholds met. Does NOT trigger for: opinions, preferences, how-to instructions, or when user explicitly wants quick answer.

0
installs
▌
Label Function Analysis · bogheorghiu
"What is this label DOING?" - Unbundle a loaded label (extremist, denier, conspiracy theorist, apologist, shill) into observation, intent, mechanism, and actor; autopsy the debate axis the label enforces; run cui-bono on the label itself; test whether the replacement axis is falsifiable. Use when (1) a label is carrying an argument that evidence should carry, (2) a source or thesis is dismissed by category rather than content, (3) both camps ping-pong on an axis that never resolves, (4) you catch the analysis reaching for a respectability label instead of a reason. Does NOT trigger for: labels used descriptively with the evidence attached.

0
installs
▌
Source Omission Analysis · bogheorghiu
"What is everyone NOT saying about this?" - After any multi-source research sweep, analyze what each perspective is SILENT about. Omissions reveal structural position more reliably than statements. Use when (1) after completing multi-source research, (2) comparing coverage across ideological positions, (3) a claim appears in some sources but not others, (4) evaluating media bias or narrative framing.

0
installs
▌
Self Improving Investigation · bogheorghiu
Am I investigating, or just confirming what I already believe? Self-correcting research methodology combining blind worker agents, nested iteration loops, and dialectic synthesis. Use when (1) research requires factual certainty not just plausibility, (2) topic has high bias risk, (3) multiple perspectives must be systematically tested, (4) user explicitly requests deep/thorough investigation, (5) previous single-pass research proved insufficient. Integrates with iterative-loop-engine and deep-investigation-protocol.

0
installs
▌
Ground Level Triangulation · bogheorghiu bundle
"What do the people with different stakes say, in their own languages?" - Map a contested geopolitical claim across language-publics with different, independent stakes: the implicated state's own primary documents, the affected party's language and nearest kin languages, non-official native voices, non-aligned neighbors, anonymous boards (skeptical use). Use when (1) a claim is bloc-contested, (2) the evidence base so far is English-language or one-bloc-sourced, (3) a verdict hinges on what a population experiences or believes, (4) building or extending a channel map for a language-public. Decision rule: convergence across independent publics grounds a claim; origin-concentration in one node weakens it — symmetrically. Does NOT trigger for: product/tech research or claims with no cross-bloc dimension (use deep-investigation-protocol's language pass).

0
installs
▌
Deep Investigation Protocol · bogheorghiu bundle
"What is REALLY at stake here? And for whom?" - STOP. When the matter involves trustworthiness, purchasing decisions, "which is better or more reliable", brand comparisons, marketing claims, corporate behavior, "convince me otherwise", or post-purchase "was this good?" - USE THIS. For technical specs affecting quality (TLC vs QLC, component sourcing) use Light Touch mode. Search and verify even if you think you know. Does NOT trigger for: what to watch/eat/wear, how-to instructions, when/where/who founded, or explicit "just tell me quick."

0
installs
▌
Video Transcript Extraction · bogheorghiu
How do I get the transcript of this video? Platform-aware extraction for any video source — YouTube, local files, or other platforms. Use when (1) need to transcribe a video for analysis, (2) user provides a video URL, (3) building a knowledge base from video content. Provides multiple methods with guided fallback chain (captions > Whisper > web services). Does NOT trigger for: watching videos, video editing, or non-transcript tasks.

0
installs
▌
Manufactured Confusion Detection · bogheorghiu
"Is this fog organic, or engineered?" - Inverse of manufactured-consensus-detection: test whether noise, contradiction, and over-supplied mutually exclusive explanations around a claim are organic uncertainty or engineered to prevent ANY conclusion. Use when (1) every source tells a different story with suspicious completeness, (2) obvious questions stay unanswered while exotic ones get saturated coverage, (3) contradictory leaks arrive faster than verification is possible, (4) "we may never know" circulates where evidence should exist. Does NOT trigger for: ordinary uncertainty from genuinely thin evidence, or fresh events still developing.

0
installs
▌
Manufactured Consensus Detection · bogheorghiu bundle
"Are these sources agreeing independently, or echoing the same origin?" - When multiple sources converge on the same claim in similar language, test whether this is genuine independent agreement or coordinated messaging from a single origin. Use when (1) multiple independent sources say the same thing in similar language, (2) convergence warning fires during verification, (3) evaluating media campaigns or narrative coordination, (4) investigating PR/comms strategy behind claims.

0
installs
▌
Windows Wsl Security Verification · bogheorghiu bundle
Am I compromised? After supply-chain news — a poisoned npm/PyPI package, a malicious VS Code extension, a backdoored dep that ran as you — this runs a guided IOC triage of a Windows + WSL2 dev box, then trims the attack surface the next compromise would use. WSL side: known-bad package versions, ld.so.preload, persistence (systemd/cron/autostart), planted SSH keys, shell-rc injection, executable .pth. Windows side: full AV scan (a third-party AV makes Defender passive — one scan, not two), second-opinion scan, Sysinternals Autoruns with VirusTotal, code --list-extensions, scheduled tasks, BYOVD-class drivers. Carries the discriminators that stop false alarms: filename IOCs via find not grep, VT named-family verdicts over aggregate labels, web-filter blocks vs infections. Fires on "am I hacked", "did I get owned", a named bad package or CVE in your dependency chain, or an AV detection you're unsure how to read. Windows/WSL-specific; verifies — does not harden. A clean result raises confidence, never proves.

0
installs

38 published skills