research-reporting

A workflow for turning machine-learning experiment runs and analysis files into structured research notes.

In plain words
What is it for?
Use it to start and update notes, summarize completed runs, compare results, extract hypotheses from evaluation or loss data, and suggest evidence-based actions for the next run.
Why use it?
It keeps experiment findings, evidence, failures, and next steps in one consistent record as a run progresses.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/profsynapse/synaptic-tuner/research-reporting
Any agent
npx skills add ProfSynapse/Synaptic-Tuner --skill research-reporting
Clone the repo
git clone --depth 1 https://github.com/ProfSynapse/Synaptic-Tuner

Made for: Claude Code, Codex.

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,234 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00089 $0.01234
Opus 5 $0.00044 $0.00617
Sonnet 5 $0.00018 $0.00247
Haiku 4.5 $0.00009 $0.00123

Measured 3d ago against content hash 4459e5711f2b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research-reporting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/research-reporting/SKILL.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Reporting

Generate compact research notes that are easy to read and easy to parse later.

Use This Skill When

  • The user wants a research note, experiment summary, post-run analysis, or structured markdown output.
  • The source of truth is an experiment bundle under .tracking/experiments/<id>/.
  • The output should include stable frontmatter and explicit evidence for claims.
  • The note should be created early and updated through the lifecycle of one experiment.

Default Workflow

  1. Resolve the experiment id and open .tracking/experiments/<id>/experiment.json.
  2. If spec_path is present, read the experiment spec so the note captures actual config numbers instead of only outcome artifacts.
  3. Read primary analysis artifacts in this order:
    • analysis/experiment_summary.json
    • analysis/next_run_candidates.json
    • analysis/hypothesis_context.json
    • analysis/run_matrix.csv
  4. Read failure slices only if you need representative examples:
    • analysis/failure_slices/eval_failures.jsonl
    • analysis/failure_slices/high_loss_examples.jsonl
  5. Read stage lineage files when you need provenance, timing, commit, hardware, or cost details.
  6. Write the note from assets/research_note_template.md.

Load reference/artifact-map.md when you need to know which artifact supports which section.

Lifecycle Modes

Use the same note template for all three modes:

  1. Launch note:
    • Create the note as soon as the experiment is launched or selected.
    • Fill identity, config, and known runtime fields.
    • Leave future metrics and recommendation fields empty.
  2. Stage update:
    • Re-open the same note after training, evaluation, loss, or analysis completes.
    • Update only the fields now supported by artifacts.
    • Preserve prior fields unless newer canonical artifacts supersede them.
  3. Final note:
    • After analysis/recommendation, ensure the note contains the final status, observed outcomes, hypotheses, and next-run recommendation.

Read the full file on GitHub · 109 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 109 lines · 89 tokens per session scan A 4459e5711f2b

Subscribe to this mod's changes

research-reporting is a skill published in the GitHub repository ProfSynapse/Synaptic-Tuner (27 stars, last pushed 3d ago), licensed MIT. It adds 89 tokens to every session and 1,234 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

html-ppt-hermes-cyber-terminal

OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.

nexu-io/open-design · 53 tokens

bigquery-ai-ml

Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…

google/skills · 104 tokens

ondb

A logical analysis and reasoning tool for AI. Use when decomposing documents into structured knowledge, querying entities and relations, validating consistency, or indexing files. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", "analyze this document", entity CRUD, or cross-skill…

x-cmd/x-cmd · 71 tokens

auditing-subgroup-fairness

Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…

maziyarpanahi/openmed · 148 tokens