$ latest --releases

Agent DX CLI Scale

A 7-axis, 0-21 scoring scale for evaluating how well a CLI is designed for AI agents rather than humans — machine-readable output, raw payload input, schema introspection, context-window discipline, input hardening, safety rails, and agent knowledge packaging.

Long-Horizon Agent Prompting

Design the launch prompt for an agent working autonomously for hours or days — a pseudo-formal task brief with an exact success predicate, an enumerated non-counting-outcomes list, adversarial verification, and effort floors, because persistence pressure against a loose spec produces confident non-solutions.

Planning with Files

Persistent, file-based planning for multi-step AI-agent work — task_plan.md, findings.md, and progress.md on disk, a 2-action rule for capturing multimodal findings before they're lost, a 3-strike error protocol, and a 5-question reboot test to verify state survives a compaction.

Secret Scan and Rotation

Find committed credentials in a repository's working tree and full history, triage real secrets from test fixtures, and drive rotation-first remediation — with an absolute rule against ever printing a secret's actual value, even during the scan itself.

Self-Improvement Loop Design

Design systems where the harness itself is the optimization target — an optimization ladder from prompt to context to workflow to harness code, a two-split empirical acceptance gate, an outside-the-loop invariant for the evaluator, and a catalog of documented reward-hacking and collapse failure modes.

Skill Security Inspector

Review an AI agent skill before installing it using two independent lines — static scanner evidence plus source-aware semantic judgment — checking purpose fit, permission fit, sensitive access, external transmission, execution risk, and persistence, down to a clear APPROVE, CAUTION, or REJECT verdict.

Tool Interface Design for Agents

Design agent-facing tools as contracts an agent must infer entirely from the description alone — the consolidation principle over narrow overlapping tools, architectural reduction toward primitives, actionable error-recovery messages, and an 8-point audit checklist.

Academic Research

Academic Research

Creative Thinking Frameworks for Research

Eight cognitive-science-grounded frameworks for AI and CS research ideation — Koestler's bisociation, Gentner's structure-mapping analogies, Boden's constraint transformation, TRIZ-style negation, Kauffman's adjacent possible, and Rothenberg's Janusian synthesis — with a combined protocol and a block-to-framework unblocking table.

Creative Writing

Creative Writing

Clean User-Facing Text

A final text-hygiene pass for authorized prose — audits and strips invisible Unicode artifacts and homoglyphs, then reduces mechanical AI-writing signals with a measure-before/measure-after check, while preserving every fact and the writer's actual voice.

Equity Research

Equity Research

Fundamental Stock Analysis Framework

A rigorous, sector-relative, multi-factor equity analysis process for Indian (NSE/BSE) and US/global listed companies — document-first sourcing that never invents a number, a recency gate that catches superseded data, forensic and IPO modes, and an adversarial challenge pass before delivery.

15 minutes

Productivity